95 citations · 471 across the 52 of their papers we have counts for
19 papers · 1 filter
Omni-IO Skills: Harnessing Your Agent Omni-Native
Yanlin Li, Mingyang Hao, Shengqiong Wu +3
General-purpose agents can plan, reason, and act over long horizons, yet their production capabilities remain fragmented across text, images, audio, video, documents, 3D assets, an…
LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
Jundong Xu, Hao Fei, Huichi Zhou +6
Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Pr…
NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations
Meng Luo, Han Zhang, Shengqiong Wu +3
This paper describes the architecture of our system developed for Task 3 of SemEval-2024: Multimodal Emotion-Cause Analysis in Conversations. Our project targets the challenges of…
Grammar Induction from Visual, Speech and Text
Yu Zhao, Hao Fei, Shengqiong Wu +3
Grammar Induction could benefit from rich heterogeneous signals, such as text, vision, and acoustics. In the process, features from distinct modalities essentially serve complement…
PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis
Meng Luo, Hao Fei, Bobo Li +6
While existing Aspect-based Sentiment Analysis (ABSA) has received extensive effort and advancement, there are still gaps in defining a more holistic research target seamlessly int…
Modeling Unified Semantic Discourse Structure for High-quality Headline Generation
Minghui Xu, Hao Fei, Fei Li +4
Headline generation aims to summarize a long document with a short, catchy title that reflects the main idea. This requires accurately capturing the core document semantics, which…
DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs
Yiyun Xiong, Mengwei Dai, Fei Li +5
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…
Revisiting Conversation Discourse for Dialogue Disentanglement
Bobo Li, Hao Fei, Fei Li +5
Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by…
ECQED: Emotion-Cause Quadruple Extraction in Dialogs
Li Zheng, Donghong Ji, Fei Li +5
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 practica…
LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model
Hao Fei, Shengqiong Wu, Jingye Li +6
Universally modeling all typical information extraction tasks (UIE) with one generative language model (GLM) has revealed great potential by the latest study, where various IE pred…
DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis
Bobo Li, Hao Fei, Fei Li +8
The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limi…
Entity-centered Cross-document Relation Extraction
Fengqi Wang, Fei Li, Hao Fei +6
Relation Extraction (RE) is a fundamental task of information extraction, which has attracted a large amount of research attention. Previous studies focus on extracting the relatio…
Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph
Hao Fei, Shengqiong Wu, Meishan Zhang +2
Conversational semantic role labeling (CSRL) is a newly proposed task that uncovers the shallow semantic structures in a dialogue text. Unfortunately several important characterist…
Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction
Shunjie Chen, Xiaochuan Shi, Jingye Li +4
Emotion cause pair extraction (ECPE), as one of the derived subtasks of emotion cause analysis (ECA), shares rich inter-related features with emotion extraction (EE) and cause extr…
OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction
Hu Cao, Jingye Li, Fangfang Su +6
Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text. Most prior work focuses on extracti…
Unified Named Entity Recognition as Word-Word Relation Classification
Jingye Li, Hao Fei, Jiang Liu +5
So far, named entity recognition (NER) has been involved with three major types, including flat, overlapped (aka. nested), and discontinuous NER, which have mostly been studied ind…
Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labeling
Shengqiong Wu, Hao Fei, Fei Li +4
Unified opinion role labeling (ORL) aims to detect all possible opinion structures of 'opinion-holder-target' in one shot, given a text. The existing transition-based unified metho…
Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge
Shengqiong Wu, Hao Fei, Yafeng Ren +2
In this paper, we propose to enhance the pair-wise aspect and opinion terms extraction (PAOTE) task by incorporating rich syntactic knowledge. We first build a syntax fusion encode…
Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning
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. Most existing works treat ALD as re…