no code implementations • CCL 2020 • Hengrui Guo, Zhongqing Wang, Peifeng Li, Qiaoming Zhu
面向社交媒体的事件聚类旨在根据事件特征对短文本聚类。目前, 事件聚类模型主要分为无监督模型和有监督模型。无监督模型聚类效果较差, 有监督模型依赖大量标注数据。基于此, 本文提出了一种半监督事件聚类模型(SemiEC), 该模型在小规模标注数据的基础上, 利用LSTM表征事件, 利用线性模型计算文本相似度, 进行增量聚类, 利用增量聚类产生的标注数据对模型再训练, 结束后对不确定样本再聚类。实验表明, SemiEC的性能相比其他模型均有所提高。
no code implementations • Findings (ACL) 2022 • Xiaotong Jiang, Qingqing Zhao, Yunfei Long, Zhongqing Wang
In this paper, we introduce a new task called synesthesia detection, which aims to extract the sensory word of a sentence, and to predict the original and synesthetic sensory modalities of the corresponding sensory word.
no code implementations • CCL 2020 • Mengyu Guan, Zhongqing Wang, Shoushan Li, Guodong Zhou
现有的对话系统中存在着生成“好的”、“我不知道”等无意义的安全回复问题。日常对话中, 对话者通常围绕特定的主题进行讨论且每句话都有明显的情感和意图。因此该文提出了基于对话约束的回复生成模型, 即在Seq2Seq模型的基础上, 结合对对话的主题、情感、意图的识别。该方法对生成回复的主题、情感和意图进行约束, 从而生成具有合理的情感和意图且与对话主题相关的回复。实验证明, 该文提出的方法能有效地提高生成回复的质量。
1 code implementation • ACL 2022 • Chenhua Chen, Zhiyang Teng, Zhongqing Wang, Yue Zhang
Dependency trees have been intensively used with graph neural networks for aspect-based sentiment classification.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • 30 Oct 2023 • Xuefeng Bai, Jialong Wu, Yulong Chen, Zhongqing Wang, Yue Zhang
Constituency parsing is a fundamental yet unsolved natural language processing task.
1 code implementation • 15 Jun 2023 • Xiaoyi Bao, Xiaotong Jiang, Zhongqing Wang, Yue Zhang, Guodong Zhou
To address these challenges, we propose an opinion tree parsing model, aiming to parse all the sentiment elements from an opinion tree, which is much faster, and can explicitly reveal a more comprehensive and complete aspect-level sentiment structure.
no code implementations • 26 May 2021 • Yong Qian, Zhongqing Wang, Rong Xiao, Chen Chen, Haihong Tang
Previous studies show effective of pre-trained language models for sentiment analysis.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • COLING 2020 • Zhongqing Wang, Xiujun Zhu, Yue Zhang, Shoushan Li, Guodong Zhou
Sentiment forecasting in dialog aims to predict the polarity of next utterance to come, and can help speakers revise their utterances in sentimental utterances generation.
no code implementations • Findings of the Association for Computational Linguistics 2020 • WeiSheng Zhang, Kaisong Song, Yangyang Kang, Zhongqing Wang, Changlong Sun, Xiaozhong Liu, Shoushan Li, Min Zhang, Luo Si
As an important research topic, customer service dialogue generation tends to generate generic seller responses by leveraging current dialogue information.
no code implementations • IJCNLP 2019 • Xiabing Zhou, Zhongqing Wang, Shoushan Li, Guodong Zhou, Min Zhang
Accordingly, we propose a Neural Personal Discrimination (NPD) approach to address above challenges by determining personal attributes from posts, and connecting relevant posts with similar attributes to jointly learn their emotions.
no code implementations • COLING 2018 • Qingying Sun, Zhongqing Wang, Qiaoming Zhu, Guodong Zhou
In addition, since the influences of different linguistic information are different, we propose a hierarchical attention network to weigh the importance of various linguistic information, and learn the mutual attention between the document and the linguistic information.
no code implementations • EMNLP 2017 • Zhongqing Wang, Yue Zhang, Ching-Yun Chang
There has been a recent line of work automatically learning scripts from unstructured texts, by modeling narrative event chains.
no code implementations • EMNLP 2017 • Zhongqing Wang, Yue Zhang
We present opinion recommendation, a novel task of jointly generating a review with a rating score that a certain user would give to a certain product which is unreviewed by the user, given existing reviews to the product by other users, and the reviews that the user has given to other products.
no code implementations • 6 Feb 2017 • Zhongqing Wang, Yue Zhang
We present opinion recommendation, a novel task of jointly predicting a custom review with a rating score that a certain user would give to a certain product or service, given existing reviews and rating scores to the product or service by other users, and the reviews that the user has given to other products and services.
no code implementations • COLING 2016 • Zhongqing Wang, Yue Zhang, Sophia Lee, Shoushan Li, Guodong Zhou
Visualization of the attention layers illustrates that the model selects qualitatively informative words.