Ying Zhang

Also published as: Joy Ying Zhang


2024

pdf bib
DPDLLM: A Black-box Framework for Detecting Pre-training Data from Large Language Models
Baohang Zhou | Zezhong Wang | Lingzhi Wang | Hongru Wang | Ying Zhang | Kehui Song | Xuhui Sui | Kam-Fai Wong
Findings of the Association for Computational Linguistics ACL 2024

The success of large language models (LLM) benefits from large-scale model parameters and large amounts of pre-training data. However, the textual data for training LLM can not be confirmed to be legal because they are crawled from different web sites. For example, there are copyrighted articles, personal reviews and information in the pre-training data for LLM which are illegal. To address the above issue and develop legal LLM, we propose to detect the pre-training data from LLM in a pure black-box way because the existing LLM services only return the generated text. The previous most related works are the membership inference attack (MIA) on machine learning models to detect the training data from them. But the existing methods are based on analyzing the output probabilities of models which are unrealistic to LLM services. To tackle the problem, we firstly construct the benchmark datasets by collecting textual data from different domains as the seen and unseen pre-training data for LLMs. Then, we investigate a black-box framework named DPDLLM, with the only access to the generated texts from LLM for detecting textual data whether was used to train it. In the proposed framework, we exploit GPT-2 as the reference model to fit the textual data and feed the generated text from LLM into it to acquire sequence probabilities as the significant feature for detection. The experimental results on the benchmark datasets demonstrate that DPDLLM is effective on different popular LLMs and outperforms the existing methods.

pdf bib
MELOV: Multimodal Entity Linking with Optimized Visual Features in Latent Space
Xuhui Sui | Ying Zhang | Yu Zhao | Kehui Song | Baohang Zhou | Xiaojie Yuan
Findings of the Association for Computational Linguistics ACL 2024

Multimodal entity linking (MEL), which aligns ambiguous mentions within multimodal contexts to referent entities from multimodal knowledge bases, is essential for many natural language processing applications. Previous MEL methods mainly focus on exploring complex multimodal interaction mechanisms to better capture coherence evidence between mentions and entities by mining complementary information. However, in real-world social media scenarios, vision modality often exhibits low quality, low value, or low relevance to the mention. Integrating such information directly will backfire, leading to a weakened consistency between mentions and their corresponding entities. In this paper, we propose a novel latent space vision feature optimization framework MELOV, which combines inter-modality and intra-modality optimizations to address these challenges. For the inter-modality optimization, we exploit the variational autoencoder to mine shared information and generate text-based visual features. For the intra-modality optimization, we consider the relationships between mentions and build graph convolutional network to aggregate the visual features of semantic similar neighbors. Extensive experiments on three benchmark datasets demonstrate the superiority of our proposed framework.

pdf bib
Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback
Chengfeng Dou | Ying Zhang | Zhi Jin | Wenpin Jiao | Haiyan Zhao | Yongqiang Zhao | Zhengwei Tao
Findings of the Association for Computational Linguistics ACL 2024

The utilization of large language models for medical dialogue generation has attracted considerable attention due to its potential to enhance response richness and coherence. While previous studies have made strides in optimizing model performance, there is a pressing need to bolster the model’s capacity for diagnostic logic to ensure patient safety. In response to this need, we propose an approach termed preference learning from process feedback (PLPF), which involves integrating the doctor’s diagnostic logic into LLMs. PLPF encompasses three key components: rule modeling, preference data generation, and preference alignment. These components collectively serve to train the model to adhere to the diagnostic process. Our experimental results, utilizing Standardized Patient Testing, demonstrate that PLPF enhances the diagnostic accuracy of the baseline model in medical conversations by 17.6%, surpassing the performance of traditional approaches. Moreover, PLPF exhibits effectiveness in both multi-round and single-round dialogue tasks, thereby highlighting its potential in improving medical dialogue generation. Our dataset is available at https://github.com/Chengfeng-Dou/SpTesting.

pdf bib
Bring Invariant to Variant: A Contrastive Prompt-based Framework for Temporal Knowledge Graph Forecasting
Ying Zhang | Xinying Qian | Yu Zhao | Baohang Zhou | Kehui Song | Xiaojie Yuan
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Temporal knowledge graph forecasting aims to reason over known facts to complete the missing links in the future. Existing methods are highly dependent on the structures of temporal knowledge graphs and commonly utilize recurrent or graph neural networks for forecasting. However, entities that are infrequently observed or have not been seen recently face challenges in learning effective knowledge representations due to insufficient structural contexts. To address the above disadvantages, in this paper, we propose a Contrastive Prompt-based framework with Entity background information for TKG forecasting, which we named CoPET. Specifically, to bring the time-invariant entity background information to time-variant structural information, we employ a dual encoder architecture consisting of a candidate encoder and a query encoder. A contrastive learning framework is used to encourage the query representation to be closer to the candidate representation. We further propose three kinds of trainable time-variant prompts aimed at capturing temporal structural information. Experiments on two datasets demonstrate that our method is effective and stays competitive in inference with limited structural information. Our code is available at https://github.com/qianxinying/CoPET.

pdf bib
Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation
Chengfeng Dou | Ying Zhang | Yanyuan Chen | Zhi Jin | Wenpin Jiao | Haiyan Zhao | Yu Huang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Large Language Models (LLMs) have made significant progress recently. However, their practical use in healthcare is hindered by their tendency to generate hallucinations. One specific type, called snowballing hallucination, occurs when LLMs encounter misleading information, and poses a security threat to LLMs. To understand how well LLMs can resist these hallucination, we create the Chinese Medical Hallucination Evaluation benchmark (CMHE). This benchmark can be used to evaluate LLMs’ ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations. The creation of this benchmark involves a combination of manual and model-based approaches. In addition, we use ICD-10 as well as MeSH, two specialized glossaries, to aid in the evaluation. Our experiments show that the LLM struggles to identify fake medical terms and makes poor diagnoses in distracting environments. However, improving the model’s understanding of medical concepts can help it resist interference to some extent.

pdf bib
Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation
Xumeng Liu | Wenya Guo | Ying Zhang | Xubo Liu | Yu Zhao | Shenglong Yu | Xiaojie Yuan
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Knowledge-based Visual Question Generation aims to generate visual questions with outside knowledge other than the image. Existing approaches are answer-aware, which incorporate answers into the question-generation process. However, these methods just focus on leveraging the semantics of inputs to propose questions, ignoring the logical coherence among generated questions (Q), images (V), answers (A), and corresponding acquired outside knowledge (K). It results in generating many non-expected questions with low quality, lacking insight and diversity, and some of them are even without any corresponding answer. To address this issue, we inject logical verification into the processes of knowledge acquisition and question generation, which is defined as LVˆ2-Net. Through checking the logical structure among V, A, K, ground-truth and generated Q twice in the whole KB-VQG procedure, LVˆ2-Net can propose diverse and insightful knowledge-based visual questions. And experimental results on two commonly used datasets demonstrate the superiority of LVˆ2-Net. Our code will be released to the public soon.

pdf bib
MCIL: Multimodal Counterfactual Instance Learning for Low-resource Entity-based Multimodal Information Extraction
Baohang Zhou | Ying Zhang | Kehui Song | Hongru Wang | Yu Zhao | Xuhui Sui | Xiaojie Yuan
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Multimodal information extraction (MIE) is a challenging task which aims to extract the structural information in free text coupled with the image for constructing the multimodal knowledge graph. The entity-based MIE tasks are based on the entity information to complete the specific tasks. However, the existing methods only investigated the entity-based MIE tasks under supervised learning with adequate labeled data. In the real-world scenario, collecting enough data and annotating the entity-based samples are time-consuming, and impractical. Therefore, we propose to investigate the entity-based MIE tasks under the low-resource settings. The conventional models are prone to overfitting on limited labeled data, which can result in poor performance. This is because the models tend to learn the bias existing in the limited samples, which can lead them to model the spurious correlations between multimodal features and task labels. To provide a more comprehensive understanding of the bias inherent in multimodal features of MIE samples, we decompose the features into image, entity, and context factors. Furthermore, we investigate the causal relationships between these factors and model performance, leveraging the structural causal model to delve into the correlations between the input features and output labels. Based on this, we propose the multimodal counterfactual instance learning framework to generate the counterfactual instances by the interventions on the limited observational samples. In the framework, we analyze the causal effect of the counterfactual instances and exploit it as a supervisory signal to maximize the effect for reducing the bias and improving the generalization of the model. Empirically, we evaluate the proposed method on the two public MIE benchmark datasets and the experimental results verify the effectiveness of it.

2023

pdf bib
Bidirectional Transformer Reranker for Grammatical Error Correction
Ying Zhang | Hidetaka Kamigaito | Manabu Okumura
Findings of the Association for Computational Linguistics: ACL 2023

Pre-trained seq2seq models have achieved state-of-the-art results in the grammatical error correction task. However, these models still suffer from a prediction bias due to their unidirectional decoding. Thus, we propose a bidirectional Transformer reranker (BTR), that re-estimates the probability of each candidate sentence generated by the pre-trained seq2seq model. The BTR preserves the seq2seq-style Transformer architecture but utilizes a BERT-style self-attention mechanism in the decoder to compute the probability of each target token by using masked language modeling to capture bidirectional representations from the target context. For guiding the reranking, the BTR adopts negative sampling in the objective function to minimize the unlikelihood. During inference, the BTR gives final results after comparing the reranked top-1 results with the original ones by an acceptance threshold. Experimental results show that, in reranking candidates from a pre-trained seq2seq model, T5-base, the BTR on top of T5-base could yield 65.47 and 71.27 F0.5 scores on the CoNLL-14 and BEA test sets, respectively, and yield 59.52 GLEU score on the JFLEG corpus, with improvements of 0.36, 0.76 and 0.48 points compared with the original T5-base. Furthermore, when reranking candidates from T5-large, the BTR on top of T5-base improved the original T5-large by 0.26 points on the BEA test set.

pdf bib
AoM: Detecting Aspect-oriented Information for Multimodal Aspect-Based Sentiment Analysis
Ru Zhou | Wenya Guo | Xumeng Liu | Shenglong Yu | Ying Zhang | Xiaojie Yuan
Findings of the Association for Computational Linguistics: ACL 2023

Multimodal aspect-based sentiment analysis (MABSA) aims to extract aspects from text-image pairs and recognize their sentiments. Existing methods make great efforts to align the whole image to corresponding aspects. However, different regions of the image may relate to different aspects in the same sentence, and coarsely establishing image-aspect alignment will introduce noise to aspect-based sentiment analysis (i.e., visual noise). Besides, the sentiment of a specific aspect can also be interfered by descriptions of other aspects (i.e., textual noise). Considering the aforementioned noises, this paper proposes an Aspect-oriented Method (AoM) to detect aspect-relevant semantic and sentiment information. Specifically, an aspect-aware attention module is designed to simultaneously select textual tokens and image blocks that are semantically related to the aspects. To accurately aggregate sentiment information, we explicitly introduce sentiment embedding into AoM, and use a graph convolutional network to model the vision-text and text-text interaction. Extensive experiments demonstrate the superiority of AoM to existing methods.

pdf bib
From Alignment to Entailment: A Unified Textual Entailment Framework for Entity Alignment
Yu Zhao | Yike Wu | Xiangrui Cai | Ying Zhang | Haiwei Zhang | Xiaojie Yuan
Findings of the Association for Computational Linguistics: ACL 2023

Entity Alignment (EA) aims to find the equivalent entities between two Knowledge Graphs (KGs). Existing methods usually encode the triples of entities as embeddings and learn to align the embeddings, which prevents the direct interaction between the original information of the cross-KG entities. Moreover, they encode the relational triples and attribute triples of an entity in heterogeneous embedding spaces, which prevents them from helping each other. In this paper, we transform both triples into unified textual sequences, and model the EA task as a bi-directional textual entailment task between the sequences of cross-KG entities. Specifically, we feed the sequences of two entities simultaneously into a pre-trained language model (PLM) and propose two kinds of PLM-based entity aligners that model the entailment probability between sequences as the similarity between entities. Our approach captures the unified correlation pattern of two kinds of information between entities, and explicitly models the fine-grained interaction between original entity information. The experiments on five cross-lingual EA datasets show that our approach outperforms the state-of-the-art EA methods and enables the mutual enhancement of the heterogeneous information. Codes are available at https://github.com/OreOZhao/TEA.

pdf bib
Structure and Label Constrained Data Augmentation for Cross-domain Few-shot NER
Jingyi Zhang | Ying Zhang | Yufeng Chen | Jinan Xu
Findings of the Association for Computational Linguistics: EMNLP 2023

Cross-domain few-shot named entity recognition (NER) is a challenging task that aims to recognize entities in target domains with limited labeled data by leveraging relevant knowledge from source domains. However, domain gaps limit the effect of knowledge transfer and harm the performance of NER models. In this paper, we analyze those domain gaps from two new perspectives, i.e., entity annotations and entity structures and leverage word-to-tag and word-to-word relations to model them, respectively. Moreover, we propose a novel method called Structure and Label Constrained Data Augmentation (SLC-DA) for Cross-domain Few-shot NER, which novelly design a label constrained pre-train task and a structure constrained optimization objectives in the data augmentation process to generate domain-specific augmented data to help NER models smoothly transition from source to target domains. We evaluate our approach on several standard datasets and achieve state-of-the-art or competitive results, demonstrating the effectiveness of our method in cross-domain few-shot NER.

pdf bib
Selecting Key Views for Zero-Shot Entity Linking
Xuhui Sui | Ying Zhang | Kehui Song | Baohang Zhou | Xiaojie Yuan | Wensheng Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

Entity linking, which aligns mentions in the text to entities in knowledge bases, is essential for many natural language processing tasks. Considering the real-world scenarios, recent research hotspot of entity linking has focused on the zero-shot setting, where mentions need to link to unseen entities and only the description of each entity is provided. This task challenges the language understanding ability of models to capture the coherence evidence between the mention context and entity description. However, entity descriptions often contain rich information from multiple views, and a mention with context only relates to a small part of the information. Other irrelevant information will introduce noise, which interferes with models to make the right judgments. Furthermore, the existence of these information also makes it difficult to synthesize key information. To solve these problems, we select key views from descriptions and propose a KVZEL framework for zero-shot entity linking. Specifically, our KVZEL first adopts unsupervised clustering to form sub views. Then, it employs a mention-aware key views selection module to iteratively accumulate mention-focused views. This puts emphasis on capturing mention-related information and allows long-range key information integration. Finally, we aggregate key views to make the final decision. Experimental results show the effectiveness of our KVZEL and it achieves the new state-of-the-art on the zero-shot entity linking dataset.

pdf bib
Licon: A Diverse, Controllable and Challenging Linguistic Concept Learning Benchmark
Shenglong Yu | Ying Zhang | Wenya Guo | Zhengkun Zhang | Ru Zhou | Xiaojie Yuan
Findings of the Association for Computational Linguistics: EMNLP 2023

Concept Learning requires learning the definition of a general category from given training examples. Most of the existing methods focus on learning concepts from images. However, the visual information cannot present abstract concepts exactly, which struggles the introduction of novel concepts related to known concepts (e.g., ‘Plant’‘Asteroids’). In this paper, inspired by the fact that humans learn most concepts through linguistic description, we introduce Linguistic Concept Learning benchmark (Licon), where concepts in diverse forms (e.g., plain attributes, images, and text) are defined by linguistic descriptions. The difficulty to learn novel concepts can be controlled by the number of attributes or the hierarchical relationships between concepts. The diverse and controllable concepts are used to support challenging evaluation tasks, including concept classification, attribute prediction, and concept relationship recognition. In addition, we design an entailment-based concept learning method (EnC) to model the relationship among concepts. Extensive experiments demonstrate the effectiveness of EnC. The benchmark will be released to the public soon.

pdf bib
Incorporating Object-Level Visual Context for Multimodal Fine-Grained Entity Typing
Ying Zhang | Wenbo Fan | Kehui Song | Yu Zhao | Xuhui Sui | Xiaojie Yuan
Findings of the Association for Computational Linguistics: EMNLP 2023

Fine-grained entity typing (FGET) aims to assign appropriate fine-grained types to entity mentions within their context, which is an important foundational task in natural language processing. Previous approaches for FGET only utilized textual context information. However, in the form of short text, the contextual semantic information is often insufficient for FGET. In many real-world scenarios, text is often accompanied by images, and the visual context is valuable for FGET. To this end, we firstly propose a new task called multimodal fine-grained entity typing (MFGET). Then we construct a large-scale dataset for multimodal fine-grained entity typing called MFIGER based on FIGER. To fully leverage both textual and visual information, we propose a novel Multimodal Object-Level Visual Context Network (MOVCNet). MOVCNet can capture fine-grained semantic information by detecting objects in images, and effectively merge both textual and visual context. Experimental results demonstrate that our approach achieves superior classification performance compared to previous text-based approaches.

pdf bib
BioFEG: Generate Latent Features for Biomedical Entity Linking
Xuhui Sui | Ying Zhang | Xiangrui Cai | Kehui Song | Baohang Zhou | Xiaojie Yuan | Wensheng Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Biomedical entity linking is an essential task in biomedical text processing, which aims to map entity mentions in biomedical text, such as clinical notes, to standard terms in a given knowledge base. However, this task is challenging due to the rarity of many biomedical entities in real-world scenarios, which often leads to a lack of annotated data for them. Limited by understanding these unseen entities, traditional biomedical entity linking models suffer from multiple types of linking errors. In this paper, we propose a novel latent feature generation framework BioFEG to address these challenges. Specifically, our BioFEG leverages domain knowledge to train a generative adversarial network, which generates latent semantic features of corresponding mentions for unseen entities. Utilizing these features, we fine-tune our entity encoder to capture fine-grained coherence information of unseen entities and better understand them. This allows models to make linking decisions more accurately, particularly for ambiguous mentions involving rare entities. Extensive experiments on the two benchmark datasets demonstrate the superiority of our proposed framework.

2022

pdf bib
A Span-based Multimodal Variational Autoencoder for Semi-supervised Multimodal Named Entity Recognition
Baohang Zhou | Ying Zhang | Kehui Song | Wenya Guo | Guoqing Zhao | Hongbin Wang | Xiaojie Yuan
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Multimodal named entity recognition (MNER) on social media is a challenging task which aims to extract named entities in free text and incorporate images to classify them into user-defined types. However, the annotation for named entities on social media demands a mount of human efforts. The existing semi-supervised named entity recognition methods focus on the text modal and are utilized to reduce labeling costs in traditional NER. However, the previous methods are not efficient for semi-supervised MNER. Because the MNER task is defined to combine the text information with image one and needs to consider the mismatch between the posted text and image. To fuse the text and image features for MNER effectively under semi-supervised setting, we propose a novel span-based multimodal variational autoencoder (SMVAE) model for semi-supervised MNER. The proposed method exploits modal-specific VAEs to model text and image latent features, and utilizes product-of-experts to acquire multimodal features. In our approach, the implicit relations between labels and multimodal features are modeled by multimodal VAE. Thus, the useful information of unlabeled data can be exploited in our method under semi-supervised setting. Experimental results on two benchmark datasets demonstrate that our approach not only outperforms baselines under supervised setting, but also improves MNER performance with less labeled data than existing semi-supervised methods.

pdf bib
MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion
Yu Zhao | Xiangrui Cai | Yike Wu | Haiwei Zhang | Ying Zhang | Guoqing Zhao | Ning Jiang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Multimodal knowledge graph completion (MKGC) aims to predict missing entities in MKGs. Previous works usually share relation representation across modalities. This results in mutual interference between modalities during training, since for a pair of entities, the relation from one modality probably contradicts that from another modality. Furthermore, making a unified prediction based on the shared relation representation treats the input in different modalities equally, while their importance to the MKGC task should be different. In this paper, we propose MoSE, a Modality Split representation learning and Ensemble inference framework for MKGC. Specifically, in the training phase, we learn modality-split relation embeddings for each modality instead of a single modality-shared one, which alleviates the modality interference. Based on these embeddings, in the inference phase, we first make modality-split predictions and then exploit various ensemble methods to combine the predictions with different weights, which models the modality importance dynamically. Experimental results on three KG datasets show that MoSE outperforms state-of-the-art MKGC methods. Codes are available at https://github.com/OreOZhao/MoSE4MKGC.

pdf bib
PM2F2N: Patient Multi-view Multi-modal Feature Fusion Networks for Clinical Outcome Prediction
Ying Zhang | Baohang Zhou | Kehui Song | Xuhui Sui | Guoqing Zhao | Ning Jiang | Xiaojie Yuan
Findings of the Association for Computational Linguistics: EMNLP 2022

Clinical outcome prediction is critical to the condition prediction of patients and management of hospital capacities. There are two kinds of medical data, including time series signals recorded by various devices and clinical notes in electronic health records (EHR), which are used for two common prediction targets: mortality and length of stay. Traditional methods focused on utilizing time series data but ignored clinical notes. With the development of deep learning, natural language processing (NLP) and multi-modal learning methods are exploited to jointly model the time series and clinical notes with different modals. However, the existing methods failed to fuse the multi-modal features of patients from different views. Therefore, we propose the patient multi-view multi-modal feature fusion networks for clinical outcome prediction. Firstly, from patient inner view, we propose to utilize the co-attention module to enhance the fine-grained feature interaction between time series and clinical notes from each patient. Secondly, the patient outer view is the correlation between patients, which can be reflected by the structural knowledge in clinical notes. We exploit the structural information extracted from clinical notes to construct the patient correlation graph, and fuse patients’ multi-modal features by graph neural networks (GNN). The experimental results on MIMIC-III benchmark demonstrate the superiority of our method.

pdf bib
Improving Zero-Shot Entity Linking Candidate Generation with Ultra-Fine Entity Type Information
Xuhui Sui | Ying Zhang | Kehui Song | Baohang Zhou | Guoqing Zhao | Xin Wei | Xiaojie Yuan
Proceedings of the 29th International Conference on Computational Linguistics

Entity linking, which aims at aligning ambiguous entity mentions to their referent entities in a knowledge base, plays a key role in multiple natural language processing tasks. Recently, zero-shot entity linking task has become a research hotspot, which links mentions to unseen entities to challenge the generalization ability. For this task, the training set and test set are from different domains, and thus entity linking models tend to be overfitting due to the tendency of memorizing the properties of entities that appear frequently in the training set. We argue that general ultra-fine-grained type information can help the linking models to learn contextual commonality and improve their generalization ability to tackle the overfitting problem. However, in the zero-shot entity linking setting, any type information is not available and entities are only identified by textual descriptions. Thus, we first extract the ultra-fine entity type information from the entity textual descriptions. Then, we propose a hierarchical multi-task model to improve the high-level zero-shot entity linking candidate generation task by utilizing the entity typing task as an auxiliary low-level task, which introduces extracted ultra-fine type information into the candidate generation task. Experimental results demonstrate the effectiveness of utilizing the ultra-fine entity type information and our proposed method achieves state-of-the-art performance.

pdf bib
Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances
Yike Wu | Yu Zhao | Shiwan Zhao | Ying Zhang | Xiaojie Yuan | Guoqing Zhao | Ning Jiang
Proceedings of the 29th International Conference on Computational Linguistics

Despite the great progress of Visual Question Answering (VQA), current VQA models heavily rely on the superficial correlation between the question type and its corresponding frequent answers (i.e., language priors) to make predictions, without really understanding the input. In this work, we define the training instances with the same question type but different answers as superficially similar instances, and attribute the language priors to the confusion of VQA model on such instances. To solve this problem, we propose a novel training framework that explicitly encourages the VQA model to distinguish between the superficially similar instances. Specifically, for each training instance, we first construct a set that contains its superficially similar counterparts. Then we exploit the proposed distinguishing module to increase the distance between the instance and its counterparts in the answer space. In this way, the VQA model is forced to further focus on the other parts of the input beyond the question type, which helps to overcome the language priors. Experimental results show that our method achieves the state-of-the-art performance on VQA-CP v2. Codes are available at Distinguishing-VQA.

2021

pdf bib
Generic Mechanism for Reducing Repetitions in Encoder-Decoder Models
Ying Zhang | Hidetaka Kamigaito | Tatsuya Aoki | Hiroya Takamura | Manabu Okumura
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)

Encoder-decoder models have been commonly used for many tasks such as machine translation and response generation. As previous research reported, these models suffer from generating redundant repetition. In this research, we propose a new mechanism for encoder-decoder models that estimates the semantic difference of a source sentence before and after being fed into the encoder-decoder model to capture the consistency between two sides. This mechanism helps reduce repeatedly generated tokens for a variety of tasks. Evaluation results on publicly available machine translation and response generation datasets demonstrate the effectiveness of our proposal.

pdf bib
A Language Model-based Generative Classifier for Sentence-level Discourse Parsing
Ying Zhang | Hidetaka Kamigaito | Manabu Okumura
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Discourse segmentation and sentence-level discourse parsing play important roles for various NLP tasks to consider textual coherence. Despite recent achievements in both tasks, there is still room for improvement due to the scarcity of labeled data. To solve the problem, we propose a language model-based generative classifier (LMGC) for using more information from labels by treating the labels as an input while enhancing label representations by embedding descriptions for each label. Moreover, since this enables LMGC to make ready the representations for labels, unseen in the pre-training step, we can effectively use a pre-trained language model in LMGC. Experimental results on the RST-DT dataset show that our LMGC achieved the state-of-the-art F1 score of 96.72 in discourse segmentation. It further achieved the state-of-the-art relation F1 scores of 84.69 with gold EDU boundaries and 81.18 with automatically segmented boundaries, respectively, in sentence-level discourse parsing.

pdf bib
Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition
Ying Zhang | Fandong Meng | Yufeng Chen | Jinan Xu | Jie Zhou
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization
Baohang Zhou | Xiangrui Cai | Ying Zhang | Xiaojie Yuan
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)

Medical named entity recognition (NER) and normalization (NEN) are fundamental for constructing knowledge graphs and building QA systems. Existing implementations for medical NER and NEN are suffered from the error propagation between the two tasks. The mispredicted mentions from NER will directly influence the results of NEN. Therefore, the NER module is the bottleneck of the whole system. Besides, the learnable features for both tasks are beneficial to improving the model performance. To avoid the disadvantages of existing models and exploit the generalized representation across the two tasks, we design an end-to-end progressive multi-task learning model for jointly modeling medical NER and NEN in an effective way. There are three level tasks with progressive difficulty in the framework. The progressive tasks can reduce the error propagation with the incremental task settings which implies the lower level tasks gain the supervised signals other than errors from the higher level tasks to improve their performances. Besides, the context features are exploited to enrich the semantic information of entity mentions extracted by NER. The performance of NEN profits from the enhanced entity mention features. The standard entities from knowledge bases are introduced into the NER module for extracting corresponding entity mentions correctly. The empirical results on two publicly available medical literature datasets demonstrate the superiority of our method over nine typical methods.

2014

pdf bib
Jibiki-LINKS: a tool between traditional dictionaries and lexical networks for modelling lexical resources
Ying Zhang | Mathieu Mangeot | Valérie Bellynck | Christian Boitet
Proceedings of the 4th Workshop on Cognitive Aspects of the Lexicon (CogALex)

2013

pdf bib
Measuring the Structural Importance through Rhetorical Structure Index
Narine Kokhlikyan | Alex Waibel | Yuqi Zhang | Joy Ying Zhang
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Complex terminologies management - the case of acronyms (Gestion des terminologies riches : l’exemple des acronymes) [in French]
Ying Zhang | Mathieu Mangeot
Proceedings of TALN 2013 (Volume 2: Short Papers)

pdf bib
iMAG : MT-postediting, translation quality evaluation and parallel corpus production (iMAG : post-édition, évaluation de qualité de TA et production d’un corpus parallèle) [in French]
Lingxiao Wang | Ying Zhang
Proceedings of TALN 2013 (Volume 3: System Demonstrations)

2012

pdf bib
Machine Translation with Binary Feedback: a Large-Margin Approach
Avneesh Saluja | Ian Lane | Ying Zhang
Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers

Viewing machine translation as a structured classification problem has provided a gateway for a host of structured prediction techniques to enter the field. In particular, large-margin structured prediction methods for discriminative training of feature weights, such as the structured perceptron or MIRA, have started to match or exceed the performance of existing methods such as MERT. One issue with structured problems in general is the difficulty in obtaining fully structured labels, e.g., in machine translation, obtaining reference translations or parallel sentence corpora for arbitrary language pairs. Another issue, more specific to the translation domain, is the difficulty in online training of machine translation systems, since existing methods often require bilingual knowledge to correct translation output online. We propose a solution to these two problems, by demonstrating a way to incorporate binary-labeled feedback (i.e., feedback on whether a translation hypothesis is a “good” or understandable one or not), a form of supervision that can be easily integrated in an online manner, into a machine translation framework. Experimental results show marked improvement by incorporating binary feedback on unseen test data, with gains exceeding 5.5 BLEU points.

pdf bib
Integrating MT with Digital Collections for Multilingual Information Access
Jiangping Chen | Olajumoke Agozu | Wenqian Zhao | Cheng Chieh Lien | Ryan Knudson | Ying Zhang
Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Commercial MT User Program

This paper describes the role of machine translation (MT) for multilingual information access, a service that is desired by digital libraries that wish to provide cross-cultural access to their collections. To understand the performance of MT, we have developed HeMT: an integrated multilingual evaluation platform (http://txcdk-v10.unt.edu/HeMT/) to facilitate human evaluation of machine translation. The results of human evaluation using HeMT on three online MT services are reported. Challenges and benefits of crowdsourcing and collaboration based on our experience are discussed. Additionally, we present the analysis of the translation errors and propose Multi-engine MT strategies to improve translation performance.

pdf bib
Demo of iMAG Possibilities: MT-postediting, Translation Quality Evaluation, Parallel Corpus Production
Ling Xiao Wang | Ying Zhang | Christian Boitet | Valerie Bellynck
Proceedings of COLING 2012: Demonstration Papers

2011

pdf bib
Context-aware Language Modeling for Conversational Speech Translation
Avneesh Saluja | Ian Lane | Ying Zhang
Proceedings of Machine Translation Summit XIII: Papers

2010

pdf bib
A Language Approach to Modeling Human Behaviors
Peng-Wen Chen | Snehal Kumar Chennuru | Ying Zhang
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

The modeling of human behavior becomes more and more important due to the increasing popularity of context-aware computing and people-centric mobile applications. Inspired by the principle of action-as-language, we propose that human ambulatory behavior shares similar properties as natural languages. In addition, by exploiting this similarity, we will be able to index, recognize, cluster, retrieve, and infer high-level semantic meanings of human behaviors via the use of natural language processing techniques. In this paper, we developed a Life Logger system to help build the behavior language corpus which supports our ""Behavior as Language"" research. The constructed behavior corpus shows Zipf's distribution over the frequency of vocabularies which is aligned with our ""Behavior as Language"" assumption. Our preliminary results of using smoothed n-gram language model for activity recognition achieved an average accuracy rate of 94% in distinguishing among human ambulatory behaviors including walking, running, and cycling. This behavior-as-language corpus will enable researchers to study higher level human behavior based on the syntactic and semantic analysis of the corpus data.

2009

pdf bib
Virtual Babel: Towards Context-Aware Machine Translation in Virtual Worlds
Ying Zhang | Nguyen Bach
Proceedings of Machine Translation Summit XII: Posters

2008

pdf bib
Domain-Specific Query Translation for Multilingual Information Access using Machine Translation Augmented With Dictionaries Mined from Wikipedia
Gareth Jones | Fabio Fantino | Eamonn Newman | Ying Zhang
Proceedings of the 2nd workshop on Cross Lingual Information Access (CLIA) Addressing the Information Need of Multilingual Societies

2007

pdf bib
Enhancing image-based Arabic document translation using noisy channel correction model
Yi Chang | Ying Zhang | Stephan Vogel | Jie Yang
Proceedings of Machine Translation Summit XI: Papers

pdf bib
PanDoRA: a large-scale two-way statistical machine translation system for hand-held devices
Ying Zhang | Stephan Vogel
Proceedings of Machine Translation Summit XI: Papers

pdf bib
The CMU-UKA statistical machine translation systems for IWSLT 2007
Ian Lane | Andreas Zollmann | Thuy Linh Nguyen | Nguyen Bach | Ashish Venugopal | Stephan Vogel | Kay Rottmann | Ying Zhang | Alex Waibel
Proceedings of the Fourth International Workshop on Spoken Language Translation

This paper describes the CMU-UKA statistical machine translation systems submitted to the IWSLT 2007 evaluation campaign. Systems were submitted for three language-pairs: Japanese→English, Chinese→English and Arabic→English. All systems were based on a common phrase-based SMT (statistical machine translation) framework but for each language-pair a specific research problem was tackled. For Japanese→English we focused on two problems: first, punctuation recovery, and second, how to incorporate topic-knowledge into the translation framework. Our Chinese→English submission focused on syntax-augmented SMT and for the Arabic→English task we focused on incorporating morphological-decomposition into the SMT framework. This research strategy enabled us to evaluate a wide variety of approaches which proved effective for the language pairs they were evaluated on.

pdf bib
Multilingual Search for Cultural Heritage Archives via Combining Multiple Translation Resources
Gareth J. F. Jones | Ying Zhang | Eamonn Newman | Fabio Fantino | Franca Debole
Proceedings of the Workshop on Language Technology for Cultural Heritage Data (LaTeCH 2007).

2006

pdf bib
Distributed Language Modeling for N-best List Re-ranking
Ying Zhang | Almut Silja Hildebrand | Stephan Vogel
Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

2005

pdf bib
Competitive Grouping in Integrated Phrase Segmentation and Alignment Model
Ying Zhang | Stephan Vogel
Proceedings of the ACL Workshop on Building and Using Parallel Texts

pdf bib
An efficient phrase-to-phrase alignment model for arbitrarily long phrase and large corpora
Ying Zhang | Stephan Vogel
Proceedings of the 10th EAMT Conference: Practical applications of machine translation

pdf bib
Mining Key Phrase Translations from Web Corpora
Fei Huang | Ying Zhang | Stephan Vogel
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing

2004

pdf bib
Interpreting BLEU/NIST Scores: How Much Improvement do We Need to Have a Better System?
Ying Zhang | Stephan Vogel | Alex Waibel
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

pdf bib
Measuring confidence intervals for the machine translation evaluation metrics
Ying Zhang | Stephan Vogel
Proceedings of the 10th Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages

2003

pdf bib
The CMU statistical machine translation system
Stephan Vogel | Ying Zhang | Fei Huang | Alicia Tribble | Ashish Venugopal | Bing Zhao | Alex Waibel
Proceedings of Machine Translation Summit IX: Papers

In this paper we describe the components of our statistical machine translation system. This system combines phrase-to-phrase translations extracted from a bilingual corpus using different alignment approaches. Special methods to extract and align named entities are used. We show how a manual lexicon can be incorporated into the statistical system in an optimized way. Experiments on Chinese-to-English and Arabic-to-English translation tasks are presented.

2001

pdf bib
Adapting an Example-Based Translation System to Chinese
Ying Zhang | Ralf D. Brown | Robert E. Frederking
Proceedings of the First International Conference on Human Language Technology Research

pdf bib
Towards Automatic Sign Translation
Jie Yang | Jiang Gao | Ying Zhang | Alex Waibel
Proceedings of the First International Conference on Human Language Technology Research

pdf bib
Pre-processing of bilingual corpora for Mandarin-English EBMT
Ying Zhang | Ralf Brown | Robert Frederking | Alon Lavie
Proceedings of Machine Translation Summit VIII

Pre-processing of bilingual corpora plays an important role in Example-Based Machine Translation (EBMT) and Statistical-Based Machine Translation (SBMT). For our Mandarin-English EBMT system, pre-processing includes segmentation for Mandarin, bracketing for English and building a statistical dictionary from the corpora. We used the Mandarin segmenter from the Linguistic Data Consortium (LDC). It uses dynamic programming with a frequency dictionary to segment the text. Although the frequency dictionary is large, it does not completely cover the corpora. In this paper, we describe the work we have done to improve the segmentation for Mandarin and the bracketing process for English to increase the length of English phrases. A statistical dictionary is built from the aligned bilingual corpus. It is used as feedback to segmentation and bracketing to re-segment / re-bracket the corpus. The process iterates several times to achieve better results. The final results of the corpus pre-processing are a segmented/bracketed aligned bilingual corpus and a statistical dictionary. We achieved positive results by increasing the average length of Chinese terms about 60% and 10% for English. The statistical dictionary gained about a 30% increase in coverage.