Yicheng Zou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yicheng Zou has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Bolin Zhu
Tianjin Normal University
2 shared publications - Chong Zhang
Department of Electrical and Computer Engineering, National University of Singapore, Singapore
2 shared publications - Qi Zhang
Fudan University, China
2 shared publications - Tao Gui
Fudan University, China
2 shared publications Xingwu Hu
School of Computer Science Fudan University
2 shared publications- Zhengyan Li
College of Liberal Arts and Sciences, National University of Defense Technology, Changsha 410073, China
2 shared publications
Latest Publications
- 15 November 2023
- Published by Springer Nature
- p. 522-534
Reversible Data Hiding Based on Adaptive Embedding with Local Complexity
- 15 November 2023
- Published by Springer Nature
- p. 522-534
Reversible Data Hiding Based on Adaptive Embedding with Local Complexity
- Open Access
Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training
Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews. We notice that about 30% of reviews do not contain obvious opinion words, but still convey clear human-aware sentiment orientation, which is known as implicit sentiment. However, recent neural network-based approaches paid little attention to implicit sentiment entailed in the reviews. To overcome this issue, we adopt Supervised Contrastive Pre-training on large-scale sentiment-annotated corpora retrieved from in-domain language resources. By aligning the representation of implicit sentiment expressions to those with the same sentiment label, the pre-training process leads to better capture of both implicit and explicit sentiment orientation towards aspects in reviews. Experimental results show that our method achieves state-of-the-art performance on SemEval2014 benchmarks, and comprehensive analysis validates its effectiveness on learning implicit sentiment.
Open AccessLearning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training
Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews. We notice that about 30% of reviews do not contain obvious opinion words, but still convey clear human-aware sentiment orientation, which is known as implicit sentiment. However, recent neural network-based approaches paid little attention to implicit sentiment entailed in the reviews. To overcome this issue, we adopt Supervised Contrastive Pre-training on large-scale sentiment-annotated corpora retrieved from in-domain language resources. By aligning the representation of implicit sentiment expressions to those with the same sentiment label, the pre-training process leads to better capture of both implicit and explicit sentiment orientation towards aspects in reviews. Experimental results show that our method achieves state-of-the-art performance on SemEval2014 benchmarks, and comprehensive analysis validates its effectiveness on learning implicit sentiment.
- Open Access
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
Various robustness evaluation methodologies from different perspectives have been proposed for different natural language processing (NLP) tasks. These methods have often focused on either universal or task-specific generalization capabilities. In this work, we propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) that incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint enables practitioners to automatically evaluate their models from all aspects or to customize their evaluations as desired with just a few lines of code. To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one. TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness. To validate TextFlint's utility, we performed large-scale empirical evaluations (over 67,000 evaluations) on state-of-the-art deep learning models, classic supervised methods, and real-world systems. Almost all models showed significant performance degradation, including a decline of more than 50% of BERT's prediction accuracy on tasks such as aspect-level sentiment classification, named entity recognition, and natural language inference. Therefore, we call for the robustness to be included in the model evaluation, so as to promote the healthy development of NLP technology.
Open AccessTextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
Various robustness evaluation methodologies from different perspectives have been proposed for different natural language processing (NLP) tasks. These methods have often focused on either universal or task-specific generalization capabilities. In this work, we propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) that incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint enables practitioners to automatically evaluate their models from all aspects or to customize their evaluations as desired with just a few lines of code. To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one. TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness. To validate TextFlint's utility, we performed large-scale empirical evaluations (over 67,000 evaluations) on state-of-the-art deep learning models, classic supervised methods, and real-world systems. Almost all models showed significant performance degradation, including a decline of more than 50% of BERT's prediction accuracy on tasks such as aspect-level sentiment classification, named entity recognition, and natural language inference. Therefore, we call for the robustness to be included in the model evaluation, so as to promote the healthy development of NLP technology.
- Open Access
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 80-91
Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining
Yicheng Zou, Bolin Zhu, Xingwu Hu, Tao Gui, Qi Zhang. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 80-91
Open AccessLow-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining
Yicheng Zou, Bolin Zhu, Xingwu Hu, Tao Gui, Qi Zhang. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.