no code implementations • 23 Mar 2024 • Minghui Xu, Hao Fei, Fei Li, Shengqiong Wu, Rui Sun, Chong Teng, Donghong Ji
To consolidate the efficacy of S3 graphs, we further devise a hierarchical structure pruning mechanism to dynamically screen the redundant and nonessential nodes within the graph.
1 code implementation • 21 Feb 2024 • Yuanze Ji, Bobo Li, Jun Zhou, Fei Li, Chong Teng, Donghong Ji
Multimodal Named Entity Recognition (MNER) is a pivotal task designed to extract named entities from text with the support of pertinent images.
1 code implementation • 23 Dec 2023 • Li Zheng, Hao Fei, Fei Li, Bobo Li, Lizi Liao, Donghong Ji, Chong Teng
With the proliferation of dialogic data across the Internet, the Dialogue Commonsense Multi-choice Question Answering (DC-MCQ) task has emerged as a response to the challenge of comprehending user queries and intentions.
1 code implementation • 18 Dec 2023 • Yuyang Chai, Zhuang Li, Jiahui Liu, Lei Chen, Fei Li, Donghong Ji, Chong Teng
Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines.
no code implementations • 8 Aug 2023 • Li Zheng, Fei Li, Yuyang Chai, Chong Teng, Donghong Ji
The joint task of Dialog Sentiment Classification (DSC) and Act Recognition (DAR) aims to predict the sentiment label and act label for each utterance in a dialog simultaneously.
no code implementations • 8 Aug 2023 • Bobo Li, Hao Fei, Lizi Liao, Yu Zhao, Chong Teng, Tat-Seng Chua, Donghong Ji, Fei Li
On the other hand, during the feature fusion stage, we propose a Contribution-aware Fusion Mechanism (CFM) and a Context Refusion Mechanism (CRM) for multimodal and context integration, respectively.
Ranked #5 on Emotion Recognition in Conversation on IEMOCAP
no code implementations • 8 Aug 2023 • Yiyun Xiong, Mengwei Dai, Fei Li, Hao Fei, Bobo Li, Shengqiong Wu, Donghong Ji, Chong Teng
Dialogue relation extraction (DRE) that identifies the relations between argument pairs in dialogue text, suffers much from the frequent occurrence of personal pronouns, or entity and speaker coreference.
no code implementations • 6 Jun 2023 • Jiang Liu, Hao Fei, Fei Li, Jingye Li, Bobo Li, Liang Zhao, Chong Teng, Donghong Ji
Few-shot named entity recognition (NER) exploits limited annotated instances to identify named mentions.
no code implementations • 6 Jun 2023 • Li Zheng, Donghong Ji, Fei Li, Hao Fei, Shengqiong Wu, Jingye Li, Bobo Li, Chong Teng
The existing emotion-cause pair extraction (ECPE) task, unfortunately, ignores extracting the emotion type and cause type, while these fine-grained meta-information can be practically useful in real-world applications, i. e., chat robots and empathic dialog generation.
no code implementations • 6 Jun 2023 • Bobo Li, Hao Fei, Fei Li, Shengqiong Wu, Lizi Liao, Yinwei Wei, Tat-Seng Chua, Donghong Ji
Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement requires the full understanding and harnessing of the intrinsic discourse attribute.
1 code implementation • 27 May 2023 • Zhuang Li, Yuyang Chai, Terry Yue Zhuo, Lizhen Qu, Gholamreza Haffari, Fei Li, Donghong Ji, Quan Hung Tran
Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval.
Ranked #2 on Human Judgment Correlation on Flickr8k-Expert
no code implementations • 19 Apr 2023 • Hao Fei, Tat-Seng Chua, Chenliang Li, Donghong Ji, Meishan Zhang, Yafeng Ren
In this study, we propose to enhance the ABSA robustness by systematically rethinking the bottlenecks from all possible angles, including model, data, and training.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • 10 Nov 2022 • Bobo Li, Hao Fei, Fei Li, Yuhan Wu, Jinsong Zhang, Shengqiong Wu, Jingye Li, Yijiang Liu, Lizi Liao, Tat-Seng Chua, Donghong Ji
The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • 1 Nov 2022 • Jiang Liu, Donghong Ji, Jingye Li, Dongdong Xie, Chong Teng, Liang Zhao, Fei Li
Concretely, we construct tag representations and embed them into TREM, so that TREM can treat tag and word representations as queries/keys/values and utilize self-attention to model their relationships.
1 code implementation • 29 Oct 2022 • Fengqi Wang, Fei Li, Hao Fei, Jingye Li, Shengqiong Wu, Fangfang Su, Wenxuan Shi, Donghong Ji, Bo Cai
First, we focus on input construction for our RE model and propose an entity-based document-context filter to retain useful information in the given documents by using the bridge entities in the text paths.
no code implementations • 6 Oct 2022 • Hao Fei, Shengqiong Wu, Meishan Zhang, Yafeng Ren, Donghong Ji
In this work, we investigate the integration of a latent graph for CSRL.
1 code implementation • COLING 2022 • Shunjie Chen, Xiaochuan Shi, Jingye Li, Shengqiong Wu, Hao Fei, Fei Li, Donghong Ji
We first propose a feature-task alignment to explicitly model the specific emotion-&cause-specific features and the shared interactive feature.
1 code implementation • COLING 2022 • Hu Cao, Jingye Li, Fangfang Su, Fei Li, Hao Fei, Shengqiong Wu, Bobo Li, Liang Zhao, Donghong Ji
Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text.
1 code implementation • Conference 2022 • Hao Fei, Jingye Li, Shengqiong Wu, Chenliang Li, Donghong Ji, Fei Li
In our global reasoning framework, D2G and ARG work collaboratively, iteratively performing lexical, syntactic and semantic information exchange and representation learning over the entire dialogue context.
Ranked #3 on Dialog Relation Extraction on DialogRE
1 code implementation • Conference 2022 • Hao Fei, Fei Li, Chenliang Li, Shengqiong Wu, Jingye Li, Donghong Ji
So far, aspect-based sentiment analysis (ABSA) has involved with total seven subtasks, in which, however the interactions among them have been left unexplored sufficiently.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +4
1 code implementation • ACL 2022 • Wenxuan Shi, Fei Li, Jingye Li, Hao Fei, Donghong Ji
The essential label set consists of the basic labels for this task, which are relatively balanced and applied in the prediction layer.
1 code implementation • 19 Dec 2021 • Jingye Li, Hao Fei, Jiang Liu, Shengqiong Wu, Meishan Zhang, Chong Teng, Donghong Ji, Fei Li
So far, named entity recognition (NER) has been involved with three major types, including flat, overlapped (aka.
Ranked #2 on Chinese Named Entity Recognition on OntoNotes 4
no code implementations • IEEE 2021 • Hao Fei, Yafeng Ren, Yue Zhang, Donghong Ji
Aspect-based sentiment triplet extraction (ASTE) aims at recognizing the joint triplets from texts, i. e., aspect terms, opinion expressions, and correlated sentiment polarities.
Ranked #3 on Aspect Sentiment Triplet Extraction on ASTE-Data-V2
1 code implementation • 5 Oct 2021 • Shengqiong Wu, Hao Fei, Fei Li, Donghong Ji, Meishan Zhang, Yijiang Liu, Chong Teng
Unified opinion role labeling (ORL) aims to detect all possible opinion structures of 'opinion-holder-target' in one shot, given a text.
Ranked #1 on Fine-Grained Opinion Analysis on MPQA (F1 (Opinion) metric)
1 code implementation • ACL 2021 • Fei Li, Zhichao Lin, Meishan Zhang, Donghong Ji
Second, we perform relation classification to judge whether a given pair of entity fragments to be overlapping or succession.
1 code implementation • Conference 2021 • Hao Fei, Fei Li, Bobo Li, Yijiang Liu, Yafeng Ren, Donghong Ji
A majority of research interests in irregular (eg, nested or discontinuous) named entity recognition (NER) have been paid on nested entities, while discontinuous entities received limited attention.
1 code implementation • Conference 2021 • Hao Fei, Fei Li, Bobo Li, Donghong Ji
Currently the unified semantic role labeling (SRL) that achieves predicate identification and argument role labeling in an end-to-end manner has received growing interests.
1 code implementation • 6 May 2021 • Shengqiong Wu, Hao Fei, Yafeng Ren, Donghong Ji, Jingye Li
In this paper, we propose to enhance the pair-wise aspect and opinion terms extraction (PAOTE) task by incorporating rich syntactic knowledge.
1 code implementation • 2 Jan 2021 • Hao Fei, Meishan Zhang, Bobo Li, Donghong Ji
It performs the two subtasks of SRL: predicate identification and argument role labeling, jointly.
Ranked #1 on Semantic Role Labeling on CoNLL-2009
no code implementations • COLING 2020 • Jingye Li, Donghong Ji, Fei Li, Meishan Zhang, Yijiang Liu
Emotion detection in conversations (EDC) is to detect the emotion for each utterance in conversations that have multiple speakers.
Ranked #19 on Emotion Recognition in Conversation on EmoryNLP
no code implementations • COLING 2020 • Jingye Li, Hao Fei, Donghong Ji
In this paper, we target improving the joint dialogue act recognition (DAR) and sentiment classification (SC) tasks by fully modeling the local contexts of utterances.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Hao Fei, Yafeng Ren, Donghong Ji
Recent studies show that integrating syntactic tree models with sequential semantic models can bring improved task performance, while these methods mostly employ shallow integration of syntax and semantics.
no code implementations • 19 Sep 2020 • Shengqiong Wu, Hao Fei, Donghong Ji
Aggressive language detection (ALD), detecting the abusive and offensive language in texts, is one of the crucial applications in NLP community.
no code implementations • 19 Sep 2020 • Bobo Li, Hao Fei, Yafeng Ren, Donghong Ji
Lexical chain consists of cohesion words in a document, which implies the underlying structure of a text, and thus facilitates downstream NLP tasks.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Hao Fei, Yafeng Ren, Donghong Ji
Syntax has been shown useful for various NLP tasks, while existing work mostly encodes singleton syntactic tree using one hierarchical neural network.
no code implementations • EMNLP 2020 • Hao Fei, Yafeng Ren, Donghong Ji
We consider retrofitting structure-aware Transformer-based language model for facilitating end tasks by proposing to exploit syntactic distance to encode both the phrasal constituency and dependency connection into the language model.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Hao Fei, Yafeng Ren, Donghong Ji
Current end-to-end semantic role labeling is mostly accomplished via graph-based neural models.
no code implementations • 24 Aug 2020 • Hao Fei, Meishan Zhang, Fei Li, Donghong Ji
In this paper, we fill the gap of cross-lingual SRL by proposing an end-to-end SRL model that incorporates a variety of universal features and transfer methods.
no code implementations • ACL 2020 • Qiji Zhou, Yue Zhang, Donghong Ji, Hao Tang
Abstract Meaning Representations (AMRs) capture sentence-level semantics structural representations to broad-coverage natural sentences.
no code implementations • ACL 2020 • Hao Tang, Donghong Ji, Chenliang Li, Qiji Zhou
The idea is to allow the dependency graph to guide the representation learning of the transformer encoder and vice versa.
1 code implementation • ACL 2020 • Hao Fei, Meishan Zhang, Donghong Ji
Many efforts of research are devoted to semantic role labeling (SRL) which is crucial for natural language understanding.
no code implementations • COLING 2020 • Yijiang Liu, Meishan Zhang, Donghong Ji
In this paper, we present Chinese lexical fusion recognition, a new task which could be regarded as one kind of coreference recognition.
no code implementations • 3 Mar 2020 • Jingye Li, Meishan Zhang, Donghong Ji, Yijiang Liu
Conversational emotion recognition (CER) has attracted increasing interests in the natural language processing (NLP) community.
Ranked #22 on Emotion Recognition in Conversation on EmoryNLP
no code implementations • WS 2019 • Wuti Xiong, Fei Li, Ming Cheng, Hong Yu, Donghong Ji
abstract In this article, we describe our approach for the Bacteria Biotopes relation extraction (BB-rel) subtask in the BioNLP Shared Task 2019.
no code implementations • 21 Jan 2019 • Canwen Xu, Jing Li, Xiangyang Luo, Jiaxin Pei, Chenliang Li, Donghong Ji
Recognizing and linking such fine-grained location mentions to well-defined location profiles are beneficial for retrieval and recommendation systems.
no code implementations • Pattern Recognition Letters 2017 • Fei Li, Meishan Zhang, Bo Tian, Bo Chen, Guohong Fu, Donghong Ji
We evaluate our models on two datasets for recognizing regular and irreg- ular biomedical entities.
no code implementations • 27 Aug 2016 • Fei Li, Meishan Zhang, Guohong Fu, Tao Qian, Donghong Ji
This model divides a sentence or text segment into five parts, namely two target entities and their three contexts.
no code implementations • LREC 2016 • Yanan Lu, Yue Zhang, Donghong Ji
Chinese sentences are written as sequences of characters, which are elementary units of syntax and semantics.
no code implementations • COLING 2016 • Shufeng Xiong, Yue Zhang, Donghong Ji, Yinxia Lou
Aspect phrase grouping is an important task in aspect-level sentiment analysis.