Search Results for author: Hao Fei

Found 24 papers, 14 papers with code

DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis

1 code implementation10 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

In this work, we introduce a novel task of conversational aspect-based sentiment quadruple analysis, namely DiaASQ, aiming to detect the sentiment quadruple of target-aspect-opinion-sentiment in a dialogue.

Aspect-Based Sentiment Analysis (ABSA) Opinion Mining

Entity-centered Cross-document Relation Extraction

1 code implementation29 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.

Relation Extraction

Conversation Disentanglement with Bi-Level Contrastive Learning

no code implementations27 Oct 2022 Chengyu Huang, Zheng Zhang, Hao Fei, Lizi Liao

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations.

Contrastive Learning Conversation Disentanglement +1

OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction

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.

Event Extraction

Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis

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.

Dependency Parsing Graph Attention +1

Nonautoregressive Encoder-Decoder Neural Framework for End-to-End Aspect-Based Sentiment Triplet Extraction

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.

Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labeling

1 code implementation5 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.

Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge

1 code implementation6 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.

Boundary Detection POS

End-to-end Semantic Role Labeling with Neural Transition-based Model

1 code implementation2 Jan 2021 Hao Fei, Meishan Zhang, Bobo Li, Donghong Ji

It performs the two subtasks of SRL: predicate identification and argument role labeling, jointly.

Semantic Role Labeling

Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions

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.

Language Modelling Multi-Task Learning +2

Improving Text Understanding via Deep Syntax-Semantics Communication

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.

Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning

no code implementations19 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.

Multi-Task Learning

Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain

1 code implementation19 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.

Retrofitting Structure-aware Transformer Language Model for End Tasks

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.

Language Modelling Multi-Task Learning

Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP

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.

Knowledge Distillation

Cross-lingual Semantic Role Labeling with Model Transfer

no code implementations24 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.

Semantic Role Labeling

Cannot find the paper you are looking for? You can Submit a new open access paper.