Lemao Liu


2024

pdf bib
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
Tingchen Fu | Deng Cai | Lemao Liu | Shuming Shi | Rui Yan
Findings of the Association for Computational Linguistics ACL 2024

Supervised fine-tuning (SFT) on instruction-following corpus is a crucial approach toward the alignment of large language models (LLMs). However, the performance of LLMs on standard knowledge and reasoning benchmarks tends to suffer from deterioration at the latter stage of the SFT process, echoing the phenomenon of alignment tax. Through our pilot study, we put a hypothesis that the data biases are probably one cause behind the phenomenon. To address the issue, we introduce a simple disperse-then-merge framework. To be concrete, we disperse the instruction-following data into portions and then train multiple sub-models using different data portions. Lastly, we merge multiple models into a single one via model merging techniques. Despite its simplicity, our framework outperforms various sophisticated methods such as data curation and training regularization on a series of standard knowledge and reasoning benchmarks.

pdf bib
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
Xueliang Zhao | Xinting Huang | Tingchen Fu | Qintong Li | Shansan Gong | Lemao Liu | Wei Bi | Lingpeng Kong
Findings of the Association for Computational Linguistics ACL 2024

Multimodal reasoning stands as a pivotal capability for large vision-language models (LVLMs). The integration with Domain-Specific Languages (DSL), offering precise visual representations, equips these models with the opportunity to execute more accurate reasoning in complex and professional domains. However, the vanilla Chain-of-Thought (CoT) prompting method faces challenges in effectively leveraging the unique strengths of visual and DSL representations, primarily due to their differing reasoning mechanisms. Additionally, it often falls short in addressing critical steps in multi-step reasoning tasks. To mitigate these challenges, we introduce the Bi-Modal Behavioral Alignment (BBA) prompting method, designed to maximize the potential of DSL in augmenting complex multi-modal reasoning tasks. This method initiates by guiding LVLMs to create separate reasoning chains for visual and DSL representations. Subsequently, it aligns these chains by addressing any inconsistencies, thus achieving a cohesive integration of behaviors from different modalities. Our experiments demonstrate that BBA substantially improves the performance of GPT-4V(ision) on geometry problem solving (28.34% 34.22%), chess positional advantage prediction (42.08% 46.99%) and molecular property prediction (77.47% 83.52%).

pdf bib
TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild
Huayang Li | Siheng Li | Deng Cai | Longyue Wang | Lemao Liu | Taro Watanabe | Yujiu Yang | Shuming Shi
Findings of the Association for Computational Linguistics ACL 2024

Large language models with instruction-following abilities have revolutionized the field of artificial intelligence. These models show exceptional generalizability to tackle various real-world tasks through their natural language interfaces. However, their performance heavily relies on high-quality exemplar data, which is often difficult to obtain. This challenge is further exacerbated when it comes to multimodal instruction following. We introduce TextBind, an almost annotation-free framework for empowering LLMs with multi-turn interleaved multimodal instruction-following capabilities. Our approach requires only image-caption pairs and generates multi-turn multimodal instruction-response conversations from a language model. To accommodate interleaved image-text inputs and outputs, we devise MIM, a language model-centric architecture that seamlessly integrates image encoder and decoder models. Extensive quantitative and qualitative experiments demonstrate that MIM trained on TextBind achieves remarkable generation capability in multimodal conversations compared to recent baselines.

pdf bib
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation
Cheng Yang | Guoping Huang | Mo Yu | Zhirui Zhang | Siheng Li | Mingming Yang | Shuming Shi | Yujiu Yang | Lemao Liu
Transactions of the Association for Computational Linguistics, Volume 12

Word-level AutoCompletion (WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i.e., the candidate target word is treated as a label). Since the context hidden vector itself does not take the label into account and it is projected to the label through a linear classifier, the model cannot sufficiently leverage valuable information from the source sentence as verified in our experiments, which eventually hinders its overall performance. To alleviate this issue, this work proposes an energy-based model for WLAC, which enables the context hidden vector to capture crucial information from the source sentence. Unfortunately, training and inference suffer from efficiency and effectiveness challenges, therefore we employ three simple yet effective strategies to put our model into practice. Experiments on four standard benchmarks demonstrate that our reranking-based approach achieves substantial improvements (about 6.07%) over the previous state-of-the-art model. Further analyses show that each strategy of our approach contributes to the final performance.1

pdf bib
Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models
Qihang Ai | Jiafan Li | Jincheng Dai | Jianwu Zhou | Lemao Liu | Haiyun Jiang | Shuming Shi
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Graph data organizes complex relationships and interactions between objects, facilitating advanced analysis and decision-making across different fields. In this paper, we propose a new paradigm for interactive and instructional graph data understanding and reasoning.Instead of adopting complex graph neural models or heuristic graph-to-text instruction design, we leverage Vision-Language Models (VLMs) to encode the graph images with varying structures across different domains. This paper first evaluates the capabilities of public VLMs in graph learning from multiple aspects. Then it introduces a novel instruction-following dataset for multimodal graph understanding and reasoning in English and Chinese. Besides, by fine-tuning MiniGPT-4 and LLaVA on our dataset, we achieved an accuracy increase of 5%-15% compared to baseline models, with the best-performing model attaining scores comparable to Gemini in GPT-asissted Evaluation. This research not only showcases the potential of integrating VLMs with graph data but also opens new avenues for advancements in graph data understanding.

pdf bib
Context Consistency between Training and Inference in Simultaneous Machine Translation
Meizhi Zhong | Lemao Liu | Kehai Chen | Mingming Yang | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing source-side context.However, there is a counterintuitive phenomenon about the context usage between training and inference: *e.g.*, in wait-k inference, model consistently trained with wait-k is much worse than that model inconsistently trained with wait-k' (k'≠ k) in terms of translation quality. To this end, we first investigate the underlying reasons behind this phenomenon and uncover the following two factors: 1) the limited correlation between translation quality and training loss; 2) exposure bias between training and inference. Based on both reasons, we then propose an effective training approach called context consistency training accordingly, which encourages consistent context usage between training and inference by optimizing translation quality and latency as bi-objectives and exposing the predictions to the model during the training. The experiments on three language pairs demonstrate that our SiMT system encouraging context consistency outperforms existing SiMT systems with context inconsistency for the first time.

pdf bib
On the Hallucination in Simultaneous Machine Translation
Meizhi Zhong | Kehai Chen | Zhengshan Xue | Lemao Liu | Mingming Yang | Min Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

It is widely known that hallucination is a critical issue in Simultaneous Machine Translation (SiMT) due to the absence of source-side information. While many efforts have been made to enhance performance for SiMT, few of them attempt to understand and analyze hallucination in SiMT.Therefore, we conduct a comprehensive analysis of hallucination in SiMT from two perspectives: understanding the distribution of hallucination words and the target-side context usage of them.Intensive experiments demonstrate some valuable findings and particularly show that it is possible to alleviate hallucination by decreasing the over usage of target-side information for SiMT.

2023

pdf bib
E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition
Zhen Zhang | Mengting Hu | Shiwan Zhao | Minlie Huang | Haotian Wang | Lemao Liu | Zhirui Zhang | Zhe Liu | Bingzhe Wu
Findings of the Association for Computational Linguistics: ACL 2023

Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments. Evidential deep learning (EDL) has recently been proposed as a promising solution to explicitly model predictive uncertainty for classification tasks. However, directly applying EDL to NER applications faces two challenges, i.e., the problems of sparse entities and OOV/OOD entities in NER tasks. To address these challenges, we propose a trustworthy NER framework named E-NER by introducing two uncertainty-guided loss terms to the conventional EDL, along with a series of uncertainty-guided training strategies. Experiments show that E-NER can be applied to multiple NER paradigms to obtain accurate uncertainty estimation. Furthermore, compared to state-of-the-art baselines, the proposed method achieves a better OOV/OOD detection performance and better generalization ability on OOV entities.

pdf bib
Unsupervised Keyphrase Extraction by Learning Neural Keyphrase Set Function
Mingyang Song | Haiyun Jiang | Lemao Liu | Shuming Shi | Liping Jing
Findings of the Association for Computational Linguistics: ACL 2023

We create a paradigm shift concerning building unsupervised keyphrase extraction systems in this paper. Instead of modeling the relevance between an individual candidate phrase and the document as in the commonly used framework, we formulate the unsupervised keyphrase extraction task as a document-set matching problem from a set-wise perspective, in which the document and the candidate set are globally matched in the semantic space to particularly take into account the interactions among all candidate phrases. Since it is intractable to exactly extract the keyphrase set by the matching function during the inference, we propose an approximate approach, which obtains the candidate subsets via a set extractor agent learned by reinforcement learning. Exhaustive experimental results demonstrate the effectiveness of our model, which outperforms the recent state-of-the-art unsupervised keyphrase extraction baselines by a large margin.

pdf bib
Rethinking Translation Memory Augmented Neural Machine Translation
Hongkun Hao | Guoping Huang | Lemao Liu | Zhirui Zhang | Shuming Shi | Rui Wang
Findings of the Association for Computational Linguistics: ACL 2023

This paper rethinks translation memory augmented neural machine translation (TM-augmented NMT) from two perspectives, i.e., a probabilistic view of retrieval and the variance-bias decomposition principle. The finding demonstrates that TM-augmented NMT is good at the ability of fitting data (i.e., lower bias) but is more sensitive to the fluctuations in the training data (i.e., higher variance), which provides an explanation to a recently reported contradictory phenomenon on the same translation task: TM-augmented NMT substantially advances NMT without TM under the high resource scenario whereas it fails under the low resource scenario. Then this paper proposes a simple yet effective TM-augmented NMT model to promote the variance and address the contradictory phenomenon. Extensive experiments show that the proposed TM-augmented NMT achieves consistent gains over both conventional NMT and existing TM-augmented NMT under two variance-preferable (low resource and plug-and-play) scenarios as well as the high resource scenario.

pdf bib
Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation
Guoxin Yu | Lemao Liu | Haiyun Jiang | Shuming Shi | Xiang Ao
Findings of the Association for Computational Linguistics: ACL 2023

In this paper, we aim to adapt the idea of retrieval-based neural approaches to the Aspect Sentiment Triplet Extraction (ASTE) task. Different from previous studies retrieving semantic similar neighbors, the ASTE task has its specialized challenges when adapting, i.e., the purpose includes predicting the sentiment polarity and it is usually aspect-dependent. Semantic similar neighbors with different polarities will be infeasible even counterproductive. To tackle this issue, we propose a retrieval-based neural ASTE approach, named RLI (Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation), which exploits the label information of neighbors. Given an aspect-opinion term pair, we retrieve semantic similar triplets from the training corpus and interpolate their label information into the augmented representation of the target pair. The retriever is jointly trained with the whole ASTE framework, and neighbors with both similar semantics and sentiments can be recalled with the aid of this distant supervision. In addition, we design a simple yet effective pre-train method for the retriever that implicitly encodes the label similarities. Extensive experiments and analysis on two widely-used benchmarks show that the proposed model establishes a new state-of-the-art on ASTE.

pdf bib
SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation
Xueliang Zhao | Tingchen Fu | Lemao Liu | Lingpeng Kong | Shuming Shi | Rui Yan
Findings of the Association for Computational Linguistics: ACL 2023

Logical data-to-text generation is a representative task in measuring the capabilities of both language generation and complex reasoning. Despite the introduction of reasoning skills in generation, existing works still rely on neural language models to output the final table description. However, due to the inefficacy of neural language models in complex reasoning, these methods inevitably have difficulty working out key entities in the description and might produce unfaithful descriptions. To alleviate these issues, we propose a dependency-aware symbolic reasoning framework that reasons out each entity in the table description with our designed table-compatible programming language. To figure out the dependency relationship among entities, we devise an entity scheduling mechanism to determine the order of programme synthesis such that the reasoning of an entity only relies on other “resolved” entities. Experiments on three datasets and three backbones show that ours outperforms previous methods not only in surface-level fidelity but also in logical fidelity. Notably, the proposed framework enhances GPT-2, BART and T5 with an absolute improvement of 5.7%~11.5% on SP-Acc.

pdf bib
Towards General Error Diagnosis via Behavioral Testing in Machine Translation
Junjie Wu | Lemao Liu | Dit-Yan Yeung
Findings of the Association for Computational Linguistics: EMNLP 2023

Behavioral testing offers a crucial means of diagnosing linguistic errors and assessing capabilities of NLP models. However, applying behavioral testing to machine translation (MT) systems is challenging as it generally requires human efforts to craft references for evaluating the translation quality of such systems on newly generated test cases. Existing works in behavioral testing of MT systems circumvent this by evaluating translation quality without references, but this restricts diagnosis to specific types of errors, such as incorrect translation of single numeric or currency words. In order to diagnose general errors, this paper proposes a new Bilingual Translation Pair Generation based Behavior Testing (BTPGBT) framework for conducting behavioral testing of MT systems. The core idea of BTPGBT is to employ a novel bilingual translation pair generation (BTPG) approach that automates the construction of high-quality test cases and their pseudoreferences. Experimental results on various MT systems demonstrate that BTPGBT could provide comprehensive and accurate behavioral testing results for general error diagnosis, which further leads to several insightful findings. Our code and data are available at https: //github.com/wujunjie1998/BTPGBT.

pdf bib
Retrieval-Augmented Few-shot Text Classification
Guoxin Yu | Lemao Liu | Haiyun Jiang | Shuming Shi | Xiang Ao
Findings of the Association for Computational Linguistics: EMNLP 2023

Retrieval-augmented methods are successful in the standard scenario where the retrieval space is sufficient; whereas in the few-shot scenario with limited retrieval space, this paper shows it is non-trivial to put them into practice. First, it is impossible to retrieve semantically similar examples by using an off-the-shelf metric and it is crucial to learn a task-specific retrieval metric; Second, our preliminary experiments demonstrate that it is difficult to optimize a plausible metric by minimizing the standard cross-entropy loss. The in-depth analyses quantitatively show minimizing cross-entropy loss suffers from the weak supervision signals and the severe gradient vanishing issue during the optimization. To address these issues, we introduce two novel training objectives, namely EM-L and R-L, which provide more task-specific guidance to the retrieval metric by the EM algorithm and a ranking-based loss, respectively. Extensive experiments on 10 datasets prove the superiority of the proposed retrieval augmented methods on the performance.

pdf bib
Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue
Tingchen Fu | Xueliang Zhao | Lemao Liu | Rui Yan
Findings of the Association for Computational Linguistics: EMNLP 2023

Multi-turn response selection aims to retrieve a response for a dialogue context from a candidate pool and negative sampling is the key to its retrieval performance. However, previous methods of negative samples tend to yield false negatives due to the one-to-many property in open-domain dialogue, which is detrimental to the optimization process. To deal with the problem, we propose a sequential variational ladder auto-encoder to capture the diverse one-to-many transition pattern of multiple characteristics in open-domain dialogue. The learned transition logic thus assists in identifying potential positives in disguise. Meanwhile, we propose a TRIGGER framework to adjust negative sampling in the training process such that the scope of false negatives dynamically updates according to the model capacity. Extensive experiments on two benchmarks verify the effectiveness of our approach.

pdf bib
DistillCSE: Distilled Contrastive Learning for Sentence Embeddings
Jiahao Xu | Wei Shao | Lihui Chen | Lemao Liu
Findings of the Association for Computational Linguistics: EMNLP 2023

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to provide additional supervision signals, a stronger model may be learned through knowledge distillation. However, the vanilla DistillCSE through the standard implementation of knowledge distillation only achieves marginal improvements. The quantitative analyses demonstrate its reason that the standard knowledge distillation exhibits a relatively large variance of the teacher model’s logits due to the essence of contrastive learning. To mitigate the issue induced by high variance, this paper accordingly proposed two simple yet effective solutions for knowledge distillation: a Group-P shuffling strategy as an implicit regularization and the averaging logits from multiple teacher components. Experiments on standard benchmarks demonstrate that the proposed DistillCSE outperforms many strong baseline methods and yields a new state-of-the-art performance.

pdf bib
Findings of the Word-Level AutoCompletion Shared Task in WMT 2023
Lemao Liu | Francisco Casacuberta | George Foster | Guoping Huang | Philipp Koehn | Geza Kovacs | Shuming Shi | Taro Watanabe | Chengqing Zong
Proceedings of the Eighth Conference on Machine Translation

This paper presents the overview of the second Word-Level autocompletion (WLAC) shared task for computer-aided translation, which aims to automatically complete a target word given a translation context including a human typed character sequence. We largely adhere to the settings of the previous round of the shared task, but with two main differences: 1) The typed character sequence is obtained from the typing process of human translators to demonstrate system performance under real-world scenarios when preparing some type of testing examples; 2) We conduct a thorough analysis on the results of the submitted systems from three perspectives. From the experimental results, we observe that translation tasks are helpful to improve the performance of WLAC models. Additionally, our further analysis shows that the semantic error accounts for a significant portion of all errors, and thus it would be promising to take this type of errors into account in future.

pdf bib
SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives
Jiahao Xu | Wei Shao | Lihui Chen | Lemao Liu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative pairs affects the model’s performance. Therefore, we propose a simple yet effective method to deal with such type of noise. Secondly, we pinpoint the rank bottleneck of current solutions to feature corruption and propose a dimension-wise contrastive learning objective to address this issue. Both proposed methods are generic and can be applied to any contrastive learning based models for sentence embeddings. Experimental results on standard benchmarks demonstrate that combining both proposed methods leads to a gain of 1.8 points compared to the strong baseline SimCSE configured with BERT base. Furthermore, applying the proposed method to DiffCSE, another strong contrastive learning based baseline, results in a gain of 1.4 points.

pdf bib
IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systems
Xu Huang | Zhirui Zhang | Ruize Gao | Yichao Du | Lemao Liu | Guoping Huang | Shuming Shi | Jiajun Chen | Shujian Huang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

We present IMTLab, an open-source end-to-end interactive machine translation (IMT) system platform that enables researchers to quickly build IMT systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. IMTLab treats the whole interactive translation process as a task-oriented dialogue with a human-in-the-loop setting, in which human interventions can be explicitly incorporated to produce high-quality, error-free translations. To this end, a general communication interface is designed to support the flexible IMT architectures and user policies. Based on the proposed design, we construct a simulated and real interactive environment to achieve end-to-end evaluation and leverage the framework to systematically evaluate previous IMT systems. Our simulated and manual experiments show that the prefix-constrained decoding approach still gains the lowest editing cost in the end-to-end evaluation, while BiTIIMT achieves comparable editing cost with a better interactive experience.

pdf bib
Rethinking Word-Level Auto-Completion in Computer-Aided Translation
Xingyu Chen | Lemao Liu | Guoping Huang | Zhirui Zhang | Mingming Yang | Shuming Shi | Rui Wang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Word-level auto-completion (WLAC) plays a crucial role in Computer-Assisted Translation. While previous studies have primarily focused on designing complex model architectures, this paper takes a different perspective by rethinking the fundamental question: what kind of words are good auto-completions? We introduce a measurable criterion to address this question and discover that existing WLAC models often fail to meet this criterion. Building upon this observation, we propose an effective approach to enhance WLAC performance by promoting adherence to the criterion. Notably, the proposed approach is general and can be applied to various encoder-based architectures. Through extensive experiments, we demonstrate that our approach outperforms the top-performing system submitted to the WLAC shared tasks in WMT2022, while utilizing significantly smaller model sizes.

pdf bib
Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer
Ruize Gao | Zhirui Zhang | Yichao Du | Lemao Liu | Rui Wang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Nearest Neighbor Machine Translation (kNN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain-specific token-level retrieval. However, the reasons underlying its success have not been thoroughly investigated. In this paper, we comprehensively analyze kNN-MT through theoretical and empirical studies. Initially, we provide new insights into the working mechanism of kNN-MT as an efficient technique to implicitly execute gradient descent on the output projection layer of NMT, indicating that it is a specific case of model fine-tuning. Subsequently, we conduct multi-domain experiments and word-level analysis to examine the differences in performance between kNN-MT and entire-model fine-tuning. Our findings suggest that: (i) Incorporating kNN-MT with adapters yields comparable translation performance to fine-tuning on in-domain test sets, while achieving better performance on out-of-domain test sets; (ii) Fine-tuning significantly outperforms kNN-MT on the recall of in-domain low-frequency words, but this gap could be bridged by optimizing the context representations with additional adapter layers.

pdf bib
On the Compositional Generalization in Versatile Open-domain Dialogue
Tingchen Fu | Xueliang Zhao | Lemao Liu | Rui Yan
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Previous research has demonstrated the potential of multi-task learning to foster a conversational agent’s ability to acquire a variety of skills. However, these approaches either suffer from interference among different datasets (also known as negative transfer), or fail to effectively reuse knowledge and skills learned from other datasets. In contrast to previous works, we develop a sparsely activated modular network: (1) We propose a well-rounded set of operators and instantiate each operator with an independent module; (2) We formulate dialogue generation as the execution of a generated programme which recursively composes and assembles modules. Extensive experiments on 9 datasets verify the efficacy of our methods through automatic evaluation and human evaluation. Notably, our model outperforms state-of-the-art supervised approaches on 4 datasets with only 10% training data thanks to the modular architecture and multi-task learning.

pdf bib
Sen2Pro: A Probabilistic Perspective to Sentence Embedding from Pre-trained Language Model
Lingfeng Shen | Haiyun Jiang | Lemao Liu | Shuming Shi
Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)

2022

pdf bib
On the Evaluation Metrics for Paraphrase Generation
Lingfeng Shen | Lemao Liu | Haiyun Jiang | Shuming Shi
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings that disobey conventional wisdom: (1) Reference-free metrics achieve better performance than their reference-based counterparts. (2) Most commonly used metrics do not align well with human annotation.Underlying reasons behind the above findings are explored through additional experiments and in-depth analyses.Based on the experiments and analyses, we propose ParaScore, a new evaluation metric for paraphrase generation. It possesses the merits of reference-based and reference-free metrics and explicitly models lexical divergence. Based on our analysis and improvements, our proposed reference-based outperforms than reference-free metrics.Experimental results demonstrate that ParaScore significantly outperforms existing metrics.

pdf bib
Neural Machine Translation with Contrastive Translation Memories
Xin Cheng | Shen Gao | Lemao Liu | Dongyan Zhao | Rui Yan
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories (TMs), we propose a new retrieval-augmented NMT to model contrastively retrieved translation memories that are holistically similar to the source sentence while individually contrastive to each other providing maximal information gain in three phases. First, in TM retrieval phase, we adopt contrastive retrieval algorithm to avoid redundancy and uninformativeness of similar translation pieces. Second, in memory encoding stage, given a set of TMs we propose a novel Hierarchical Group Attention module to gather both local context of each TM and global context of the whole TM set. Finally, in training phase, a Multi-TM contrastive learning objective is introduced to learn salient feature of each TM with respect to target sentence. Experimental results show that our framework obtains substantial improvements over strong baselines in the benchmark dataset.

pdf bib
Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure
Xueliang Zhao | Lemao Liu | Tingchen Fu | Shuming Shi | Dongyan Zhao | Rui Yan
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable ability is mainly obtained by fitting a large model with hundreds of millions of parameters on massive data in an exhaustive way, leading to inefficient running and poor interpretability. This paper proposes a novel dialogue generation model with a latent structure that is easily transferable from the general domain to downstream tasks in a lightweight and transparent way. Experiments on two benchmarks validate the effectiveness of the proposed model. Thanks to the transferable latent structure, our model is able to yield better dialogue responses than four strong baselines in terms of both automatic and human evaluations, and our model with about 22% parameters particularly delivers a 5x speedup in running time compared with the strongest baseline. Moreover, the proposed model is explainable by interpreting the discrete latent variables.

pdf bib
Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics
Jiannan Xiang | Huayang Li | Yahui Liu | Lemao Liu | Guoping Huang | Defu Lian | Shuming Shi
Findings of the Association for Computational Linguistics: ACL 2022

Current practices in metric evaluation focus on one single dataset, e.g., Newstest dataset in each year’s WMT Metrics Shared Task. However, in this paper, we qualitatively and quantitatively show that the performances of metrics are sensitive to data. The ranking of metrics varies when the evaluation is conducted on different datasets. Then this paper further investigates two potential hypotheses, i.e., insignificant data points and the deviation of i.i.d assumption, which may take responsibility for the issue of data variance. In conclusion, our findings suggest that when evaluating automatic translation metrics, researchers should take data variance into account and be cautious to report the results on unreliable datasets, because it may leads to inconsistent results with most of the other datasets.

pdf bib
Visualizing the Relationship Between Encoded Linguistic Information and Task Performance
Jiannan Xiang | Huayang Li | Defu Lian | Guoping Huang | Taro Watanabe | Lemao Liu
Findings of the Association for Computational Linguistics: ACL 2022

Probing is popular to analyze whether linguistic information can be captured by a well-trained deep neural model, but it is hard to answer how the change of the encoded linguistic information will affect task performance. To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality. Its key idea is to obtain a set of models which are Pareto-optimal in terms of both objectives. From this viewpoint, we propose a method to optimize the Pareto-optimal models by formalizing it as a multi-objective optimization problem. We conduct experiments on two popular NLP tasks, i.e., machine translation and language modeling, and investigate the relationship between several kinds of linguistic information and task performances. Experimental results demonstrate that the proposed method is better than a baseline method. Our empirical findings suggest that some syntactic information is helpful for NLP tasks whereas encoding more syntactic information does not necessarily lead to better performance, because the model architecture is also an important factor.

pdf bib
MCPG: A Flexible Multi-Level Controllable Framework for Unsupervised Paraphrase Generation
Yi Chen | Haiyun Jiang | Lemao Liu | Rui Wang | Shuming Shi | Ruifeng Xu
Findings of the Association for Computational Linguistics: EMNLP 2022

We present MCPG: a simple and effectiveapproach for controllable unsupervised paraphrase generation, which is also flexible toadapt to specific domains without extra training. MCPG is controllable in different levels: local lexicons, global semantics, and universal styles. The unsupervised paradigm ofMCPG combines factual keywords and diversified semantic embeddings as local lexical andglobal semantic constraints. The semantic embeddings are diversified by standard dropout,which is exploited for the first time to increaseinference diversity by us. Moreover, MCPGis qualified with good domain adaptability byadding a transfer vector as a universal style constraint, which is refined from the exemplars retrieved from the corpus of the target domain in atraining-free way. Extensive experiments showthat MCPG outperforms state-of-the-art unsupervised baselines by a margin. Meanwhile,our domain-adapted MCPG also achieves competitive performance with strong supervisedbaselines even without training.

pdf bib
BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation
Yanling Xiao | Lemao Liu | Guoping Huang | Qu Cui | Shujian Huang | Shuming Shi | Jiajun Chen
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Interactive neural machine translation (INMT) is able to guarantee high-quality translations by taking human interactions into account. Existing IMT systems relying on lexical constrained decoding (LCD) enable humans to translate in a flexible translation order beyond the left-to-right. However, they typically suffer from two significant limitations in translation efficiency and quality due to the reliance on LCD. In this work, we propose a novel BiTIIMT system, Bilingual Text-Infilling for Interactive Neural Machine Translation. The key idea to BiTIIMT is Bilingual Text-infilling (BiTI) which aims to fill missing segments in a manually revised translation for a given source sentence. We propose a simple yet effective solution by casting this task as a sequence-to-sequence task. In this way, our system performs decoding without explicit constraints and makes full use of revised words for better translation prediction. Experiment results show that BiTiIMT performs significantly better and faster than state-of-the-art LCD-based IMT on three translation tasks.

pdf bib
Learning from Sibling Mentions with Scalable Graph Inference in Fine-Grained Entity Typing
Yi Chen | Jiayang Cheng | Haiyun Jiang | Lemao Liu | Haisong Zhang | Shuming Shi | Ruifeng Xu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we firstly empirically find that existing models struggle to handle hard mentions due to their insufficient contexts, which consequently limits their overall typing performance. To this end, we propose to exploit sibling mentions for enhancing the mention representations. Specifically, we present two different metrics for sibling selection and employ an attentive graph neural network to aggregate information from sibling mentions. The proposed graph model is scalable in that unseen test mentions are allowed to be added as new nodes for inference. Exhaustive experiments demonstrate the effectiveness of our sibling learning strategy, where our model outperforms ten strong baselines. Moreover, our experiments indeed prove the superiority of sibling mentions in helping clarify the types for hard mentions.

pdf bib
Rethinking Negative Sampling for Handling Missing Entity Annotations
Yangming Li | Lemao Liu | Shuming Shi
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Negative sampling is highly effective in handling missing annotations for named entity recognition (NER). One of our contributions is an analysis on how it makes sense through introducing two insightful concepts: missampling and uncertainty. Empirical studies show low missampling rate and high uncertainty are both essential for achieving promising performances with negative sampling. Based on the sparsity of named entities, we also theoretically derive a lower bound for the probability of zero missampling rate, which is only relevant to sentence length. The other contribution is an adaptive and weighted sampling distribution that further improves negative sampling via our former analysis. Experiments on synthetic datasets and well-annotated datasets (e.g., CoNLL-2003) show that our proposed approach benefits negative sampling in terms of F1 score and loss convergence. Besides, models with improved negative sampling have achieved new state-of-the-art results on real-world datasets (e.g., EC).

pdf bib
On Synthetic Data for Back Translation
Jiahao Xu | Yubin Ruan | Wei Bi | Guoping Huang | Shuming Shi | Lihui Chen | Lemao Liu
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Back translation (BT) is one of the most significant technologies in NMT research fields. Existing attempts on BT share a common characteristic: they employ either beam search or random sampling to generate synthetic data with a backward model but seldom work studies the role of synthetic data in the performance of BT. This motivates us to ask a fundamental question: what kind of synthetic data contributes to BT performance?Through both theoretical and empirical studies, we identify two key factors on synthetic data controlling the back-translation NMT performance, which are quality and importance. Furthermore, based on our findings, we propose a simple yet effective method to generate synthetic data to better trade off both factors so as to yield the better performance for BT. We run extensive experiments on WMT14 DE-EN, EN-DE, and RU-EN benchmark tasks. By employing our proposed method to generate synthetic data, our BT model significantly outperforms the standard BT baselines (i.e., beam and sampling based methods for data generation), which proves the effectiveness of our proposed methods.

pdf bib
Findings of the Word-Level AutoCompletion Shared Task in WMT 2022
Francisco Casacuberta | George Foster | Guoping Huang | Philipp Koehn | Geza Kovacs | Lemao Liu | Shuming Shi | Taro Watanabe | Chengqing Zong
Proceedings of the Seventh Conference on Machine Translation (WMT)

Recent years have witnessed rapid advancements in machine translation, but the state-of-the-art machine translation system still can not satisfy the high requirements in some rigorous translation scenarios. Computer-aided translation (CAT) provides a promising solution to yield a high-quality translation with a guarantee. Unfortunately, due to the lack of popular benchmarks, the research on CAT is not well developed compared with machine translation. In this year, we hold a new shared task called Word-level AutoCompletion (WLAC) for CAT in WMT. Specifically, we introduce some resources to train a WLAC model, and particularly we collect data from CAT systems as a part of test data for this shared task. In addition, we employ both automatic and human evaluations to measure the performance of the submitted systems, and our final evaluation results reveal some findings for the WLAC task.

2021

pdf bib
Neural Sequence Segmentation as Determining the Leftmost Segments
Yangming Li | Lemao Liu | Kaisheng Yao
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally segments natural language sentences at segment level. For every step in segmentation, it recognizes the leftmost segment of the remaining sequence. Implementations involve LSTM-minus technique to construct the phrase representations and recurrent neural networks (RNN) to model the iterations of determining the leftmost segments. We have conducted extensive experiments on syntactic chunking and Chinese part-of-speech (POS) tagging across 3 datasets, demonstrating that our methods have significantly outperformed previous all baselines and achieved new state-of-the-art results. Moreover, qualitative analysis and the study on segmenting long-length sentences verify its effectiveness in modeling long-term dependencies.

pdf bib
An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing
Yi Chen | Haiyun Jiang | Lemao Liu | Shuming Shi | Chuang Fan | Min Yang | Ruifeng Xu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET). However, there lacks a comprehensive understanding about how to make better use of the existing information sources and how they affect the performance of ZFET. In this paper, we empirically study three kinds of auxiliary information: context consistency, type hierarchy and background knowledge (e.g., prototypes and descriptions) of types, and propose a multi-source fusion model (MSF) targeting these sources. The performance obtains up to 11.42% and 22.84% absolute gains over state-of-the-art baselines on BBN and Wiki respectively with regard to macro F1 scores. More importantly, we further discuss the characteristics, merits and demerits of each information source and provide an intuitive understanding of the complementarity among them.

pdf bib
Fine-grained Entity Typing without Knowledge Base
Jing Qian | Yibin Liu | Lemao Liu | Yangming Li | Haiyun Jiang | Haisong Zhang | Shuming Shi
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Existing work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision. However, the reliance on KB means this training setting can be hampered by the lack of or the incompleteness of the KB. To alleviate this limitation, we propose a novel setting for training FET models: FET without accessing any knowledge base. Under this setting, we propose a two-step framework to train FET models. In the first step, we automatically create pseudo data with fine-grained labels from a large unlabeled dataset. Then a neural network model is trained based on the pseudo data, either in an unsupervised way or using self-training under the weak guidance from a coarse-grained Named Entity Recognition (NER) model. Experimental results show that our method achieves competitive performance with respect to the models trained on the original KB-supervised datasets.

pdf bib
Assessing Dialogue Systems with Distribution Distances
Jiannan Xiang | Yahui Liu | Deng Cai | Huayang Li | Defu Lian | Lemao Liu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Enhancing the Open-Domain Dialogue Evaluation in Latent Space
Zhangming Chan | Lemao Liu | Juntao Li | Haisong Zhang | Dongyan Zhao | Shuming Shi | Rui Yan
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Segmenting Natural Language Sentences via Lexical Unit Analysis
Yangming Li | Lemao Liu | Shuming Shi
Findings of the Association for Computational Linguistics: EMNLP 2021

The span-based model enjoys great popularity in recent works of sequence segmentation. However, each of these methods suffers from its own defects, such as invalid predictions. In this work, we introduce a unified span-based model, lexical unit analysis (LUA), that addresses all these matters. Segmenting a lexical unit sequence involves two steps. Firstly, we embed every span by using the representations from a pretraining language model. Secondly, we define a score for every segmentation candidate and apply dynamic programming (DP) to extract the candidate with the maximum score. We have conducted extensive experiments on 3 tasks, (e.g., syntactic chunking), across 7 datasets. LUA has established new state-of-the-art performances on 6 of them. We have achieved even better results through incorporating label correlations.

pdf bib
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base
Yu Feng | Jing Zhang | Gaole He | Wayne Xin Zhao | Lemao Liu | Quan Liu | Cuiping Li | Hong Chen
Findings of the Association for Computational Linguistics: EMNLP 2021

Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs). This paper targets at empowering the IR-based KBQA models with the ability of numerical reasoning for answering ordinal constrained questions. A major challenge is the lack of explicit annotations about numerical properties. To address this challenge, we propose a pretraining numerical reasoning model consisting of NumGNN and NumTransformer, guided by explicit self-supervision signals. The two modules are pretrained to encode the magnitude and ordinal properties of numbers respectively and can serve as model-agnostic plugins for any IR-based KBQA model to enhance its numerical reasoning ability. Extensive experiments on two KBQA benchmarks verify the effectiveness of our method to enhance the numerical reasoning ability for IR-based KBQA models.

pdf bib
Engage the Public: Poll Question Generation for Social Media Posts
Zexin Lu | Keyang Ding | Yuji Zhang | Jing Li | Baolin Peng | Lemao Liu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

This paper presents a novel task to generate poll questions for social media posts. It offers an easy way to hear the voice from the public and learn from their feelings to important social topics. While most related work tackles formal languages (e.g., exam papers), we generate poll questions for short and colloquial social media messages exhibiting severe data sparsity. To deal with that, we propose to encode user comments and discover latent topics therein as contexts. They are then incorporated into a sequence-to-sequence (S2S) architecture for question generation and its extension with dual decoders to additionally yield poll choices (answers). For experiments, we collect a large-scale Chinese dataset from Sina Weibo containing over 20K polls. The results show that our model outperforms the popular S2S models without exploiting topics from comments and the dual decoder design can further benefit the prediction of both questions and answers. Human evaluations further exhibit our superiority in yielding high-quality polls helpful to draw user engagements.

pdf bib
Fast and Accurate Neural Machine Translation with Translation Memory
Qiuxiang He | Guoping Huang | Qu Cui | Li Li | Lemao Liu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

It is generally believed that a translation memory (TM) should be beneficial for machine translation tasks. Unfortunately, existing wisdom demonstrates the superiority of TM-based neural machine translation (NMT) only on the TM-specialized translation tasks rather than general tasks, with a non-negligible computational overhead. In this paper, we propose a fast and accurate approach to TM-based NMT within the Transformer framework: the model architecture is simple and employs a single bilingual sentence as its TM, leading to efficient training and inference; and its parameters are effectively optimized through a novel training criterion. Extensive experiments on six TM-specialized tasks show that the proposed approach substantially surpasses several strong baselines that use multiple TMs, in terms of BLEU and running time. In particular, the proposed approach also advances the strong baselines on two general tasks (WMT news Zh->En and En->De).

pdf bib
GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation
Huayang Li | Lemao Liu | Guoping Huang | Shuming Shi
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Computer-aided translation (CAT), the use of software to assist a human translator in the translation process, has been proven to be useful in enhancing the productivity of human translators. Autocompletion, which suggests translation results according to the text pieces provided by human translators, is a core function of CAT. There are two limitations in previous research in this line. First, most research works on this topic focus on sentence-level autocompletion (i.e., generating the whole translation as a sentence based on human input), but word-level autocompletion is under-explored so far. Second, almost no public benchmarks are available for the autocompletion task of CAT. This might be among the reasons why research progress in CAT is much slower compared to automatic MT. In this paper, we propose the task of general word-level autocompletion (GWLAN) from a real-world CAT scenario, and construct the first public benchmark to facilitate research in this topic. In addition, we propose an effective method for GWLAN and compare it with several strong baselines. Experiments demonstrate that our proposed method can give significantly more accurate predictions than the baseline methods on our benchmark datasets.

pdf bib
Neural Machine Translation with Monolingual Translation Memory
Deng Cai | Yan Wang | Huayang Li | Wai Lam | Lemao Liu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Prior work has proved that Translation Memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval, we propose a new framework that uses monolingual memory and performs learnable memory retrieval in a cross-lingual manner. Our framework has unique advantages. First, the cross-lingual memory retriever allows abundant monolingual data to be TM. Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal. Experiments show that the proposed method obtains substantial improvements. Remarkably, it even outperforms strong TM-augmented NMT baselines using bilingual TM. Owning to the ability to leverage monolingual data, our model also demonstrates effectiveness in low-resource and domain adaptation scenarios.

pdf bib
TexSmart: A System for Enhanced Natural Language Understanding
Lemao Liu | Haisong Zhang | Haiyun Jiang | Yangming Li | Enbo Zhao | Kun Xu | Linfeng Song | Suncong Zheng | Botong Zhou | Dick Zhu | Xiao Feng | Tao Chen | Tao Yang | Dong Yu | Feng Zhang | ZhanHui Kang | Shuming Shi
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations

This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Compared to most previous publicly available text understanding systems and tools, TexSmart holds some unique features. First, the NER function of TexSmart supports over 1,000 entity types, while most other public tools typically support several to (at most) dozens of entity types. Second, TexSmart introduces new semantic analysis functions like semantic expansion and deep semantic representation, that are absent in most previous systems. Third, a spectrum of algorithms (from very fast algorithms to those that are relatively slow but more accurate) are implemented for one function in TexSmart, to fulfill the requirements of different academic and industrial applications. The adoption of unsupervised or weakly-supervised algorithms is especially emphasized, with the goal of easily updating our models to include fresh data with less human annotation efforts.

2020

pdf bib
On the Branching Bias of Syntax Extracted from Pre-trained Language Models
Huayang Li | Lemao Liu | Guoping Huang | Shuming Shi
Findings of the Association for Computational Linguistics: EMNLP 2020

Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing. However, this kind of methods may suffer from the branching bias issue, which will inflate the performances on languages with the same branch it biases to. In this work, we propose quantitatively measuring the branching bias by comparing the performance gap on a language and its reversed language, which is agnostic to both language models and extracting methods. Furthermore, we analyze the impacts of three factors on the branching bias, namely feature definitions, parsing algorithms, and language models. Experiments show that several existing works exhibit branching biases, and some implementations of these three factors can introduce the branching bias.

pdf bib
Touch Editing: A Flexible One-Time Interaction Approach for Translation
Qian Wang | Jiajun Zhang | Lemao Liu | Guoping Huang | Chengqing Zong
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

We propose a touch-based editing method for translation, which is more flexible than traditional keyboard-mouse-based translation postediting. This approach relies on touch actions that users perform to indicate translation errors. We present a dual-encoder model to handle the actions and generate refined translations. To mimic the user feedback, we adopt the TER algorithm comparing between draft translations and references to automatically extract the simulated actions for training data construction. Experiments on translation datasets with simulated editing actions show that our method significantly improves original translation of Transformer (up to 25.31 BLEU) and outperforms existing interactive translation methods (up to 16.64 BLEU). We also conduct experiments on post-editing dataset to further prove the robustness and effectiveness of our method.

pdf bib
Evaluating Explanation Methods for Neural Machine Translation
Jierui Li | Lemao Liu | Huayang Li | Guanlin Li | Guoping Huang | Shuming Shi
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Recently many efforts have been devoted to interpreting the black-box NMT models, but little progress has been made on metrics to evaluate explanation methods. Word Alignment Error Rate can be used as such a metric that matches human understanding, however, it can not measure explanation methods on those target words that are not aligned to any source word. This paper thereby makes an initial attempt to evaluate explanation methods from an alternative viewpoint. To this end, it proposes a principled metric based on fidelity in regard to the predictive behavior of the NMT model. As the exact computation for this metric is intractable, we employ an efficient approach as its approximation. On six standard translation tasks, we quantitatively evaluate several explanation methods in terms of the proposed metric and we reveal some valuable findings for these explanation methods in our experiments.

pdf bib
Regularized Context Gates on Transformer for Machine Translation
Xintong Li | Lemao Liu | Rui Wang | Guoping Huang | Max Meng
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation (NMT). However, it is challenging to extend them into the advanced Transformer architecture, which is more complicated than RNN. This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer. In addition, to further reduce the bias problem in the gate mechanism, this paper proposes a regularization method to guide the learning of the gates with supervision automatically generated using pointwise mutual information. Extensive experiments on 4 translation datasets demonstrate that the proposed model obtains an averaged gain of 1.0 BLEU score over a strong Transformer baseline.

2019

pdf bib
On the Word Alignment from Neural Machine Translation
Xintong Li | Guanlin Li | Lemao Liu | Max Meng | Shuming Shi
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, this paper finds attention may almost fail to capture word alignment for some NMT models. This paper thereby proposes two methods to induce word alignment which are general and agnostic to specific NMT models. Experiments show that both methods induce much better word alignment than attention. This paper further visualizes the translation through the word alignment induced by NMT. In particular, it analyzes the effect of alignment errors on translation errors at word level and its quantitative analysis over many testing examples consistently demonstrate that alignment errors are likely to lead to translation errors measured by different metrics.

pdf bib
Understanding and Improving Hidden Representations for Neural Machine Translation
Guanlin Li | Lemao Liu | Xintong Li | Conghui Zhu | Tiejun Zhao | Shuming Shi
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Multilayer architectures are currently the gold standard for large-scale neural machine translation. Existing works have explored some methods for understanding the hidden representations, however, they have not sought to improve the translation quality rationally according to their understanding. Towards understanding for performance improvement, we first artificially construct a sequence of nested relative tasks and measure the feature generalization ability of the learned hidden representation over these tasks. Based on our understanding, we then propose to regularize the layer-wise representations with all tree-induced tasks. To overcome the computational bottleneck resulting from the large number of regularization terms, we design efficient approximation methods by selecting a few coarse-to-fine tasks for regularization. Extensive experiments on two widely-used datasets demonstrate the proposed methods only lead to small extra overheads in training but no additional overheads in testing, and achieve consistent improvements (up to +1.3 BLEU) compared to the state-of-the-art translation model.

pdf bib
Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization
Guanlin Li | Lemao Liu | Guoping Huang | Conghui Zhu | Tiejun Zhao
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Many Data Augmentation (DA) methods have been proposed for neural machine translation. Existing works measure the superiority of DA methods in terms of their performance on a specific test set, but we find that some DA methods do not exhibit consistent improvements across translation tasks. Based on the observation, this paper makes an initial attempt to answer a fundamental question: what benefits, which are consistent across different methods and tasks, does DA in general obtain? Inspired by recent theoretic advances in deep learning, the paper understands DA from two perspectives towards the generalization ability of a model: input sensitivity and prediction margin, which are defined independent of specific test set thereby may lead to findings with relatively low variance. Extensive experiments show that relatively consistent benefits across five DA methods and four translation tasks are achieved regarding both perspectives.

2018

pdf bib
Automatic Article Commenting: the Task and Dataset
Lianhui Qin | Lemao Liu | Wei Bi | Yan Wang | Xiaojiang Liu | Zhiting Hu | Hai Zhao | Shuming Shi
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Comments of online articles provide extended views and improve user engagement. Automatically making comments thus become a valuable functionality for online forums, intelligent chatbots, etc. This paper proposes the new task of automatic article commenting, and introduces a large-scale Chinese dataset with millions of real comments and a human-annotated subset characterizing the comments’ varying quality. Incorporating the human bias of comment quality, we further develop automatic metrics that generalize a broad set of popular reference-based metrics and exhibit greatly improved correlations with human evaluations.

pdf bib
Target Foresight Based Attention for Neural Machine Translation
Xintong Li | Lemao Liu | Zhaopeng Tu | Shuming Shi | Max Meng
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

In neural machine translation, an attention model is used to identify the aligned source words for a target word (target foresight word) in order to select translation context, but it does not make use of any information of this target foresight word at all. Previous work proposed an approach to improve the attention model by explicitly accessing this target foresight word and demonstrated the substantial gains in alignment task. However, this approach is useless in machine translation task on which the target foresight word is unavailable. In this paper, we propose a new attention model enhanced by the implicit information of target foresight word oriented to both alignment and translation tasks. Empirical experiments on Chinese-to-English and Japanese-to-English datasets show that the proposed attention model delivers significant improvements in terms of both alignment error rate and BLEU.

2017

pdf bib
Instance Weighting for Neural Machine Translation Domain Adaptation
Rui Wang | Masao Utiyama | Lemao Liu | Kehai Chen | Eiichiro Sumita
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model. In this paper, two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation. Empirical results on the IWSLT English-German/French tasks show that the proposed methods can substantially improve NMT performance by up to 2.7-6.7 BLEU points, outperforming the existing baselines by up to 1.6-3.6 BLEU points.

pdf bib
Neural Machine Translation with Source Dependency Representation
Kehai Chen | Rui Wang | Masao Utiyama | Lemao Liu | Akihiro Tamura | Eiichiro Sumita | Tiejun Zhao
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Source dependency information has been successfully introduced into statistical machine translation. However, there are only a few preliminary attempts for Neural Machine Translation (NMT), such as concatenating representations of source word and its dependency label together. In this paper, we propose a novel NMT with source dependency representation to improve translation performance of NMT, especially long sentences. Empirical results on NIST Chinese-to-English translation task show that our method achieves 1.6 BLEU improvements on average over a strong NMT system.

2016

pdf bib
Target-Bidirectional Neural Models for Machine Transliteration
Andrew Finch | Lemao Liu | Xiaolin Wang | Eiichiro Sumita
Proceedings of the Sixth Named Entity Workshop

pdf bib
Agreement on Target-bidirectional Neural Machine Translation
Lemao Liu | Masao Utiyama | Andrew Finch | Eiichiro Sumita
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Neural Machine Translation with Supervised Attention
Lemao Liu | Masao Utiyama | Andrew Finch | Eiichiro Sumita
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

The attention mechanism is appealing for neural machine translation, since it is able to dynamically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in alignment accuracy. In this paper, we analyze and explain this issue from the point view of reordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the supervised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.

2015

pdf bib
Neural Network Transduction Models in Transliteration Generation
Andrew Finch | Lemao Liu | Xiaolin Wang | Eiichiro Sumita
Proceedings of the Fifth Named Entity Workshop

2014

pdf bib
Search-Aware Tuning for Machine Translation
Lemao Liu | Liang Huang
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Scalable Large-Margin Structured Learning: Theory and Algorithms
Liang Huang | Kai Zhao | Lemao Liu
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: Tutorials

2013

pdf bib
Tuning SMT with a Large Number of Features via Online Feature Grouping
Lemao Liu | Tiejun Zhao | Taro Watanabe | Eiichiro Sumita
Proceedings of the Sixth International Joint Conference on Natural Language Processing

pdf bib
Additive Neural Networks for Statistical Machine Translation
Lemao Liu | Taro Watanabe | Eiichiro Sumita | Tiejun Zhao
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2012

pdf bib
Locally Training the Log-Linear Model for SMT
Lemao Liu | Hailong Cao | Taro Watanabe | Tiejun Zhao | Mo Yu | Conghui Zhu
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

pdf bib
Expected Error Minimization with Ultraconservative Update for SMT
Lemao Liu | Tiejun Zhao | Taro Watanabe | Hailong Cao | Conghui Zhu
Proceedings of COLING 2012: Posters

2011

pdf bib
A Unified and Discriminative Soft Syntactic Constraint Model for Hierarchical Phrase-based Translation
Lemao Liu | Tiejun Zhao | Chao Wang | Hailong Cao
Proceedings of Machine Translation Summit XIII: Papers

Search
Co-authors