Chang Su


2024

pdf bib
HW-TSC at TextGraphs-17 Shared Task: Enhancing Inference Capabilities of LLMs with Knowledge Graphs
Wei Tang | Xiaosong Qiao | Xiaofeng Zhao | Min Zhang | Chang Su | Yuang Li | Yinglu Li | Yilun Liu | Feiyu Yao | Shimin Tao | Hao Yang | He Xianghui
Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing

In this paper, we present an effective method for TextGraphs-17 Shared Task. This task requires selecting an entity from the candidate entities that is relevant to the given question and answer. The selection process is aided by utilizing the shortest path graph in the knowledge graph, connecting entities in the query to the candidate entity. This task aims to explore how to enhance LLMs output with KGs, although current LLMs have certain logical reasoning capabilities, they may not be certain about their own outputs, and the answers they produce may be correct by chance through incorrect paths. In this case, we have introduced a LLM prompt design strategy based on self-ranking and emotion. Specifically, we let the large model score its own answer choices to reflect its confidence in the answer. Additionally, we add emotional incentives to the prompts to encourage the model to carefully examine the questions. Our submissions was conducted under zero-resource setting, and we achieved the second place in the task with an F1-score of 0.8321.

pdf bib
CB-Whisper: Contextual Biasing Whisper Using Open-Vocabulary Keyword-Spotting
Yuang Li | Yinglu Li | Min Zhang | Chang Su | Jiawei Yu | Mengyao Piao | Xiaosong Qiao | Miaomiao Ma | Yanqing Zhao | Hao Yang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations and terminologies that are not frequently encountered in the training data. This paper presents Contextual Biasing Whisper (CB-Whisper), a novel ASR system based on OpenAI’s Whisper model that can recognize user-defined name entities by performing open-vocabulary keyword-spotting (KWS) before the decoder. The KWS module leverages text-to-speech (TTS) techniques and a convolutional neural network (CNN) classifier to match the features between the entities and the utterances. To integrate the recognized entities into the Whipser decoder and avoid hallucinations, we carefully crafted multiple prompts with spoken form hints. Experiments show that the KWS module based on Whisper encoder’s features can recognize unseen user-defined keywords effectively. More importantly, the proposed CB-Whisper substantially improves the mixed-error-rate (MER) and entity recall compared to the original Whisper model on three internal datasets and two publicly available datasets including Aishell and ACL datasets that cover English-only, Chinese-only, and code-switching scenarios.

2023

pdf bib
HW-TSC at SemEval-2023 Task 7: Exploring the Natural Language Inference Capabilities of ChatGPT and Pre-trained Language Model for Clinical Trial
Xiaofeng Zhao | Min Zhang | Miaomiao Ma | Chang Su | Yilun Liu | Minghan Wang | Xiaosong Qiao | Jiaxin Guo | Yinglu Li | Wenbing Ma
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

In this paper, we describe the multi strategy system for SemEval-2022 Task 7, This task aims to determine whether a given statement is supported by one or two Clinical Trial reports, and to identify evidence that supports the statement. This is a task that requires high natural language inference capabilities. In Subtask 1, we compare our strategy based on prompt learning and ChatGPT with a baseline constructed using BERT in zero-shot setting, and validate the effectiveness of our strategy. In Subtask 2, we fine-tune DeBERTaV3 for classification without relying on the results from Subtask 1, and we observe that early stopping can effectively prevent model overfitting, which performs well in Subtask 2. In addition, we did not use any ensemble strategies. Ultimately, we achieved the 10th place in Subtask 1 and the 2nd place in Subtask 2.

pdf bib
HW-TSC 2023 Submission for the Quality Estimation Shared Task
Yuang Li | Chang Su | Ming Zhu | Mengyao Piao | Xinglin Lyu | Min Zhang | Hao Yang
Proceedings of the Eighth Conference on Machine Translation

Quality estimation (QE) is an essential technique to assess machine translation quality without reference translations. In this paper, we focus on Huawei Translation Services Center’s (HW-TSC’s) submission to the sentence-level QE shared task, named Ensemble-CrossQE. Our system uses CrossQE, the same model architecture as our last year’s submission, which consists of a multilingual base model and a task-specific downstream layer. The input is the concatenation of the source and the translated sentences. To enhance the performance, we finetuned and ensembled multiple base models such as XLM-R, InfoXLM, RemBERT and CometKiwi. Moreover, we introduce a new corruption-based data augmentation method, which generates deletion, substitution and insertion errors in the original translation and uses a reference-based QE model to obtain pseudo scores. Results show that our system achieves impressive performance on sentence-level QE test sets and ranked the first place for three language pairs: English-Hindi, English-Tamil and English-Telegu. In addition, we participated in the error span detection task. The submitted model outperforms the baseline on Chinese-English and Hebrew-English language pairs.

2022

pdf bib
Probing Simile Knowledge from Pre-trained Language Models
Weijie Chen | Yongzhu Chang | Rongsheng Zhang | Jiashu Pu | Guandan Chen | Le Zhang | Yadong Xi | Yijiang Chen | Chang Su
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Simile interpretation (SI) and simile generation (SG) are challenging tasks for NLP because models require adequate world knowledge to produce predictions. Previous works have employed many hand-crafted resources to bring knowledge-related into models, which is time-consuming and labor-intensive. In recent years, pre-trained language models (PLMs) based approaches have become the de-facto standard in NLP since they learn generic knowledge from a large corpus. The knowledge embedded in PLMs may be useful for SI and SG tasks. Nevertheless, there are few works to explore it. In this paper, we probe simile knowledge from PLMs to solve the SI and SG tasks in the unified framework of simile triple completion for the first time. The backbone of our framework is to construct masked sentences with manual patterns and then predict the candidate words in the masked position. In this framework, we adopt a secondary training process (Adjective-Noun mask Training) with the masked language model (MLM) loss to enhance the prediction diversity of candidate words in the masked position. Moreover, pattern ensemble (PE) and pattern search (PS) are applied to improve the quality of predicted words. Finally, automatic and human evaluations demonstrate the effectiveness of our framework in both SI and SG tasks.

pdf bib
Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference
Yuxia Wang | Minghan Wang | Yimeng Chen | Shimin Tao | Jiaxin Guo | Chang Su | Min Zhang | Hao Yang
Findings of the Association for Computational Linguistics: ACL 2022

Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity. Several recent efforts have been made to acknowledge and embrace the existence of ambiguity, and explore how to capture the human disagreement distribution. In contrast with directly learning from gold ambiguity labels, relying on special resource, we argue that the model has naturally captured the human ambiguity distribution as long as it’s calibrated, i.e. the predictive probability can reflect the true correctness likelihood. Our experiments show that when model is well-calibrated, either by label smoothing or temperature scaling, it can obtain competitive performance as prior work, on both divergence scores between predictive probability and the true human opinion distribution, and the accuracy. This reveals the overhead of collecting gold ambiguity labels can be cut, by broadly solving how to calibrate the NLI network.

pdf bib
Part Represents Whole: Improving the Evaluation of Machine Translation System Using Entropy Enhanced Metrics
Yilun Liu | Shimin Tao | Chang Su | Min Zhang | Yanqing Zhao | Hao Yang
Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022

Machine translation (MT) metrics often experience poor correlations with human assessments. In terms of MT system evaluation, most metrics pay equal attentions to every sample in an evaluation set, while in human evaluation, difficult sentences often make candidate systems distinguishable via notable fluctuations in human scores, especially when systems are competitive. We find that samples with high entropy values, which though usually count less than 5%, tend to play a key role in MT evaluation: when the evaluation set is shrunk to only the high-entropy portion, correlations with human assessments are actually improved. Thus, in this paper, we propose a fast and unsupervised approach to enhance MT metrics using entropy, expanding the dimension of evaluation by introducing sentence-level difficulty. A translation hypothesis with a significantly high entropy value is considered difficult and receives a large weight in aggregation of system-level scores. Experimental results on five sub-tracks in the WMT19 Metrics shared tasks show that our proposed method significantly enhanced the performance of commonly-used MT metrics in terms of system-level correlations with human assessments, even outperforming existing SOTA metrics. In particular, all enhanced metrics exhibit overall stability in correlations with human assessments in circumstances where only competitive MT systems are included, while the corresponding vanilla metrics fail to correlate with human assessments.

pdf bib
Diformer: Directional Transformer for Neural Machine Translation
Minghan Wang | Jiaxin Guo | Yuxia Wang | Daimeng Wei | Hengchao Shang | Yinglu Li | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang
Proceedings of the 23rd Annual Conference of the European Association for Machine Translation

Autoregressive (AR) and Non-autoregressive (NAR) models have their own superiority on the performance and latency, combining them into one model may take advantage of both. Current combination frameworks focus more on the integration of multiple decoding paradigms with a unified generative model, e.g. Masked Language Model. However, the generalization can be harmful on the performance due to the gap between training objective and inference. In this paper, we aim to close the gap by preserving the original objective of AR and NAR under a unified framework. Specifically, we propose the Directional Transformer (Diformer) by jointly modelling AR and NAR into three generation directions (left-to-right, right-to-left and straight) with a newly introduced direction variable, which works by controlling the prediction of each token to have specific dependencies under that direction. The unification achieved by direction successfully preserves the original dependency assumption used in AR and NAR, retaining both generalization and performance. Experiments on 4 WMT benchmarks demonstrate that Diformer outperforms current united-modelling works with more than 1.5 BLEU points for both AR and NAR decoding, and is also competitive to the state-of-the-art independent AR and NAR models.

pdf bib
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation
Yinglu Li | Minghan Wang | Jiaxin Guo | Xiaosong Qiao | Yuxia Wang | Daimeng Wei | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang | Ying Qin
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

This paper describes the HW-TSC’s designation of the Offline Speech Translation System submitted for IWSLT 2022 Evaluation. We explored both cascade and end-to-end system on three language tracks (en-de, en-zh and en-ja), and we chose the cascade one as our primary submission. For the automatic speech recognition (ASR) model of cascade system, there are three ASR models including Conformer, S2T-Transformer and U2 trained on the mixture of five datasets. During inference, transcripts are generated with the help of domain controlled generation strategy. Context-aware reranking and ensemble based anti-interference strategy are proposed to produce better ASR outputs. For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora. Our cascade system shows competitive performance than the known offline systems in the industry and academia.

pdf bib
The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation
Minghan Wang | Jiaxin Guo | Yinglu Li | Xiaosong Qiao | Yuxia Wang | Zongyao Li | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang | Ying Qin
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

This paper presents our work in the participation of IWSLT 2022 simultaneous speech translation evaluation. For the track of text-to-text (T2T), we participate in three language pairs and build wait-k based simultaneous MT (SimulMT) model for the task. The model was pretrained on WMT21 news corpora, and was further improved with in-domain fine-tuning and self-training. For the speech-to-text (S2T) track, we designed both cascade and end-to-end form in three language pairs. The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track. The end-to-end system is a simultaneous speech translation (SimulST) model based on wait-k strategy, which is directly trained on a synthetic corpus produced by translating all texts of ASR corpora into specific target language with an offline MT model. It also contains a heuristic sentence breaking strategy, preventing it from finishing the translation before the the end of the speech. We evaluate our systems on the MUST-C tst-COMMON dataset and show that the end-to-end system is competitive to the cascade one. Meanwhile, we also demonstrate that the SimulMT model can be efficiently optimized by these approaches, resulting in the improvements of 1-2 BLEU points.

pdf bib
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
Jiaxin Guo | Yinglu Li | Minghan Wang | Xiaosong Qiao | Yuxia Wang | Hengchao Shang | Chang Su | Yimeng Chen | Min Zhang | Shimin Tao | Hao Yang | Ying Qin
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022. We design a cascade system consisted of an ASR model, machine translation model and TTS model to convert the speech from one language into another language(en-de). For the ASR part, we find that better performance can be obtained by ensembling multiple heterogeneous ASR models and performing reranking on beam candidates. And we find that the combination of context-aware reranking strategy and MT model fine-tuned on the in-domain dataset is helpful to improve the performance. Because it can mitigate the problem that the inconsistency in transcripts caused by the lack of context. Finally, we use VITS model provided officially to reproduce audio files from the translation hypothesis.

pdf bib
PingAnTech at SMM4H task1: Multiple pre-trained model approaches for Adverse Drug Reactions
Xi Liu | Han Zhou | Chang Su
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task

This paper describes the solution for the Social Media Mining for Health (SMM4H) 2022 Shared Task. We participated in Task1a., Task1b. and Task1c. To solve the problem of the presence of Twitter data, we used a pre-trained language model. We used training strategies that involved: adversarial training, head layer weighted fusion, etc., to improve the performance of the model. The experimental results show the effectiveness of our designed system. For task 1a, the system achieved an F1 score of 0.68; for task 1b Overlapping F1 score of 0.65 and a Strict F1 score of 0.49. Task 1c yields Overlapping F1 and Strict F1 scores of 0.36 and 0.30, respectively.

2021

pdf bib
Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation
Minghan Wang | Jiaxin Guo | Yimeng Chen | Chang Su | Min Zhang | Shimin Tao | Hao Yang
Proceedings of Machine Translation Summit XVIII: Research Track

Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT. To this end and we propose a transfer learning solution. Specifically and 1) A vanilla Transformer is pre-trained on massive bilingual text-only corpus to obtain prior knowledge; 2) A multimodal Transformer named VLTransformer is proposed with several components incorporated visual contexts; and 3) The parameters of VLTransformer are initialized with the pre-trained vanilla Transformer and then being fine-tuned on MMT tasks with a newly proposed method named cross-modal masking which forces the model to learn from both modalities. We evaluated on the Multi30k en-de and en-fr dataset and improving up to 8% BLEU score compared with the SOTA performance. The experimental result demonstrates that performing transfer learning with monomodal pre-trained NMT model on multimodal NMT tasks can obtain considerable boosts.

pdf bib
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
Yimeng Chen | Chang Su | Yingtao Zhang | Yuxia Wang | Xiang Geng | Hao Yang | Shimin Tao | Guo Jiaxin | Wang Minghan | Min Zhang | Yujia Liu | Shujian Huang
Proceedings of the Sixth Conference on Machine Translation

This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task. We participated in all of the three sub-tasks, including Sentence-Level Direct Assessment (DA) task, Word and Sentence-Level Post-editing Effort task and Critical Error Detection task, in all language pairs. Our systems employ the framework of Predictor-Estimator, concretely with a pre-trained XLM-Roberta as Predictor and task-specific classifier or regressor as Estimator. For all tasks, we improve our systems by incorporating post-edit sentence or additional high-quality translation sentence in the way of multitask learning or encoding it with predictors directly. Moreover, in zero-shot setting, our data augmentation strategy based on Monte-Carlo Dropout brings up significant improvement on DA sub-task. Notably, our submissions achieve remarkable results over all tasks.

pdf bib
Enhanced Metaphor Detection via Incorporation of External Knowledge Based on Linguistic Theories
Chang Su | Kechun Wu | Yijiang Chen
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021