no code implementations • EMNLP 2020 • Rui Xia, Kaizhou Xuan, Jianfei Yu
To address this limitation, we propose a state-independent and time-evolving Network (STN) for rumor detection based on fine-grained event state detection and segmentation.
1 code implementation • EMNLP 2020 • Zixiang Ding, Rui Xia, Jianfei Yu
To tackle these shortcomings, we propose two joint frameworks for ECPE: 1) multi-label learning for the extraction of the cause clauses corresponding to the specified emotion clause (CMLL) and 2) multi-label learning for the extraction of the emotion clauses corresponding to the specified cause clause (EMLL).
Ranked #3 on Emotion-Cause Pair Extraction on ECPE
no code implementations • EMNLP 2020 • Chenggong Gong, Jianfei Yu, Rui Xia
The supervised models for aspect-based sentiment analysis (ABSA) rely heavily on labeled data.
no code implementations • EMNLP 2020 • Jianfei Yu, Jing Jiang, Ling Min Serena Khoo, Hai Leong Chieu, Rui Xia
The prevalent use of social media enables rapid spread of rumors on a massive scale, which leads to the emerging need of automatic rumor verification (RV).
1 code implementation • EMNLP 2021 • Hao Chen, Rui Xia, Jianfei Yu
Data augmentation and adversarial perturbation approaches have recently achieved promising results in solving the over-fitting problem in many natural language processing (NLP) tasks including sentiment classification.
1 code implementation • NAACL 2022 • Junjie Li, Jianfei Yu, Rui Xia
As a fundamental task in opinion mining, aspect and opinion co-extraction aims to identify the aspect terms and opinion terms in reviews.
1 code implementation • EMNLP 2021 • Ziheng Liu, Rui Xia, Jianfei Yu
To address these limitations, in this work we first introduce a new Comparative Opinion Quintuple Extraction (COQE) task, to identify comparative sentences from product reviews and extract all comparative opinion quintuples (Subject, Object, Comparative Aspect, Comparative Opinion, Comparative Preference).
1 code implementation • 19 May 2024 • Fanfan Wang, Heqing Ma, Jianfei Yu, Rui Xia, Erik Cambria
The ability to understand emotions is an essential component of human-like artificial intelligence, as emotions greatly influence human cognition, decision making, and social interactions.
no code implementations • 6 Nov 2023 • Yunlong Chen, Yaming Zhang, Jianfei Yu, Li Yang, Rui Xia
However, generating the most appropriate knowledge base query code based on Natural Language Questions (NLQ) poses a significant challenge in KBQA.
1 code implementation • Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2023 • Wenjie Zheng, Jianfei Yu, Rui Xia, Shijin Wang
With the extracted face sequences, we propose a multimodal facial expression-aware emotion recognition model, which leverages the frame-level facial emotion distributions to help improve utterance-level emotion recognition based on multi-task learning.
Ranked #9 on Emotion Recognition in Conversation on MELD
Emotion Recognition in Conversation Facial Expression Recognition (FER)
1 code implementation • 29 Jun 2023 • Hongjie Cai, Nan Song, Zengzhi Wang, Qiming Xie, Qiankun Zhao, Ke Li, Siwei Wu, Shijie Liu, Jianfei Yu, Rui Xia
Aspect-based sentiment analysis is a long-standing research interest in the field of opinion mining, and in recent years, researchers have gradually shifted their focus from simple ABSA subtasks to end-to-end multi-element ABSA tasks.
no code implementations • 20 Nov 2022 • Zengzhi Wang, Rui Xia, Jianfei Yu
Aspect-Based Sentiment Analysis (ABSA) aims to provide fine-grained aspect-level sentiment information.
Ranked #5 on Aspect-Based Sentiment Analysis (ABSA) on ACOS (using extra training data)
Aspect-Based Sentiment Analysis Aspect-Category-Opinion-Sentiment Quadruple Extraction +5
1 code implementation • ACL 2022 • Yan Ling, Jianfei Yu, Rui Xia
Further analysis demonstrates the effectiveness of each pretraining task.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • 15 Oct 2021 • Fanfan Wang, Zixiang Ding, Rui Xia, Zhaoyu Li, Jianfei Yu
It is also interesting to discover emotions and their causes in conversations.
1 code implementation • ACL 2021 • Hongjie Cai, Rui Xia, Jianfei Yu
In this work, we introduce a new task, named Aspect-Category-Opinion-Sentiment (ACOS) Quadruple Extraction, with the goal to extract all aspect-category-opinion-sentiment quadruples in a review sentence and provide full support for aspect-based sentiment analysis with implicit aspects and opinions.
Aspect-Based Sentiment Analysis Aspect-Category-Opinion-Sentiment Quadruple Extraction +1
no code implementations • COLING 2020 • Hongjie Cai, Yaofeng Tu, Xiangsheng Zhou, Jianfei Yu, Rui Xia
In this work, we re-formalize the task as a category-sentiment hierarchy prediction problem, which contains a hierarchy output structure to first identify multiple aspect categories in a piece of text, and then predict the sentiment for each of the identified categories.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • ACL 2020 • Zixiang Ding, Rui Xia, Jianfei Yu
In recent years, a new interesting task, called emotion-cause pair extraction (ECPE), has emerged in the area of text emotion analysis.
Ranked #8 on Emotion-Cause Pair Extraction on ECPE
1 code implementation • ACL 2020 • Jianfei Yu, Jing Jiang, Li Yang, Rui Xia
To tackle the first issue, we propose a multimodal interaction module to obtain both image-aware word representations and word-aware visual representations.
Multi-modal Named Entity Recognition named-entity-recognition +1
no code implementations • 13 Apr 2020 • Yufei Tian, Jianfei Yu, Jing Jiang
In this paper, we study abstractive review summarization. Observing that review summaries often consist of aspect words, opinion words and context words, we propose a two-stage reinforcement learning approach, which first predicts the output word type from the three types, and then leverages the predicted word type to generate the final word distribution. Experimental results on two Amazon product review datasets demonstrate that our method can consistently outperform several strong baseline approaches based on ROUGE scores.
no code implementations • IEEE 2018 • Jianfei Yu, Jing Jiang, Rui Xia
However, most existing methods fail to explicitly consider the syntactic relations among aspect terms and opinion terms, which may lead to the inconsistencies between the model predictions and the syntactic constraints.
Aspect Term Extraction and Sentiment Classification Multi-Task Learning +2
no code implementations • EMNLP 2018 • Jianfei Yu, Lu{\'\i}s Marujo, Jing Jiang, Pradeep Karuturi, William Brendel
In this paper, we target at improving the performance of multi-label emotion classification with the help of sentiment classification.
2 code implementations • 3 Feb 2018 • Zixiang Ding, Rui Xia, Jianfei Yu, Xiang Li, Jian Yang
Deep neural networks have recently been shown to achieve highly competitive performance in many computer vision tasks due to their abilities of exploring in a much larger hypothesis space.
1 code implementation • 23 Nov 2017 • Jianfei Yu, Minghui Qiu, Jing Jiang, Jun Huang, Shuangyong Song, Wei Chu, Haiqing Chen
In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain.
no code implementations • IJCNLP 2017 • Jianfei Yu, Jing Jiang
In this paper, we study domain adaptation with a state-of-the-art hierarchical neural network for document-level sentiment classification.
no code implementations • COLING 2016 • Jianfei Yu, Jing Jiang
Relation classification is the task of classifying the semantic relations between entity pairs in text.