Liang-Yu Chen

Also published as: Liangyu Chen


2022

pdf bib
To Answer or Not To Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive Learning
Yunjie Ji | Liangyu Chen | Chenxiao Dou | Baochang Ma | Xiangang Li
Findings of the Association for Computational Linguistics: NAACL 2022

Machine Reading Comprehension with Unanswerable Questions is a difficult NLP task, challenged by the questions which can not be answered from passages.It is observed that subtle literal changes often make an answerable question unanswerable, however, most MRC models fail to recognize such changes.To address this problem, in this paper, we propose a span-based method of Contrastive Learning (spanCL) which explicitly contrast answerable questions with their answerable and unanswerable counterparts at the answer span level.With spanCL, MRC models are forced to perceive crucial semantic changes from slight literal differences.Experiments on SQuAD 2.0 dataset show that spanCL can improve baselines significantly, yielding 0.86~2.14 absolute EM improvements. Additional experiments also show that spanCL is an effective way to utilize generated questions.

pdf bib
BEIKE NLP at SemEval-2022 Task 4: Prompt-Based Paragraph Classification for Patronizing and Condescending Language Detection
Yong Deng | Chenxiao Dou | Liangyu Chen | Deqiang Miao | Xianghui Sun | Baochang Ma | Xiangang Li
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

PCL detection task is aimed at identifying and categorizing language that is patronizing or condescending towards vulnerable communities in the general media. Compared to other NLP tasks of paragraph classification, the negative language presented in the PCL detection task is usually more implicit and subtle to be recognized, making the performance of common text classification approaches disappointed. Targeting the PCL detection problem in SemEval-2022 Task 4, in this paper, we give an introduction to our team’s solution, which exploits the power of prompt-based learning on paragraph classification. We reformulate the task as an appropriate cloze prompt and use pre2trained Masked Language Models to fill the cloze slot. For the two subtasks, binary classification and multi-label classification, DeBERTa model is adopted and fine-tuned to predict masked label words of task-specific prompts. On the evaluation dataset, for binary classification, our approach achieves an F1-score of 0.6406; for multi-label classification, our approach achieves an macro-F1-score of 0.4689 and ranks first in the leaderboard.

2020

pdf bib
Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer
Chulun Zhou | Liangyu Chen | Jiachen Liu | Xinyan Xiao | Jinsong Su | Sheng Guo | Hua Wu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style, they are unable to yield desirable output sentences. In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the target style for unsupervised style transfer. Specifically, we first pretrain a style classifier, where the relevance of each input word to the original style can be quantified via layer-wise relevance propagation. In a denoising auto-encoding manner, we train an attentional Seq2seq model to reconstruct input sentences and repredict word-level previously-quantified style relevance simultaneously. In this way, this model is endowed with the ability to automatically predict the style relevance of each output word. Then, we equip the decoder of this model with a neural style component to exploit the predicted wordlevel style relevance for better style transfer. Particularly, we fine-tune this model using a carefully-designed objective function involving style transfer, style relevance consistency, content preservation and fluency modeling loss terms. Experimental results show that our proposed model achieves state-of-the-art performance in terms of both transfer accuracy and content preservation.

2014

pdf bib
A Simple Bayesian Modelling Approach to Event Extraction from Twitter
Deyu Zhou | Liangyu Chen | Yulan He
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2013

pdf bib
使用語音評分技術輔助台語語料的驗證 (Using Speech Assessment Technique for the Validation of Taiwanese Speech Corpus) [In Chinese]
Yu-Jhe Li | Chung-Che Wang | Liang-Yu Chen | Jyh-Shing Roger Jang | Ren-Yuan Lyu
Proceedings of the 25th Conference on Computational Linguistics and Speech Processing (ROCLING 2013)

pdf bib
使用語音評分技術輔助台語語料的驗證 (Using Speech Assessment Technique for the Validation of Taiwanese Speech Corpus) [In Chinese]
Yu-Jhe Li | Chung-Che Wang | Liang-Yu Chen | Jyh-Shing Roger Jang | Ren-Yuan Lyu
International Journal of Computational Linguistics & Chinese Language Processing, Volume 18, Number 4, December 2013-Special Issue on Selected Papers from ROCLING XXV

2012

pdf bib
台語關鍵詞辨識之實作與比較 (Implementation and Comparison of Keyword Spotting for Taiwanese) [In Chinese]
Chung-Che Wang | Che-Hsuan Chou | Liang-Yu Chen | Yu-Jhe Li | Jyh-Shing Jang | Hsun-Cheng Hu | Shih-Peng Lin | You-Lian Huang
Proceedings of the 24th Conference on Computational Linguistics and Speech Processing (ROCLING 2012)