Search Results for author: Hao Fei

Found 64 papers, 32 papers with code

Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing

no code implementations5 Jul 2024 Chengjie Zhou, Bobo Li, Hao Fei, Fei Li, Chong Teng, Donghong Ji

In this paper, we treat the SSA task as a dependency parsing task on partially-observed dependency trees, regarding flat spans without determined tree annotations as latent subtrees to consider internal structures of spans.

Dependency Parsing Sentiment Analysis

Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment

no code implementations27 Jun 2024 Hao Fei, Shengqiong Wu, Meishan Zhang, Min Zhang, Tat-Seng Chua, Shuicheng Yan

Then, an SG-based framework is built, where the textual SG (TSG) is encoded with a graph Transformer, while the video dynamic SG (DSG) and the HSG are modeled with a novel recurrent graph Transformer for spatial and temporal feature propagation.

Towards Semantic Equivalence of Tokenization in Multimodal LLM

no code implementations7 Jun 2024 Shengqiong Wu, Hao Fei, Xiangtai Li, Jiayi Ji, Hanwang Zhang, Tat-Seng Chua, Shuicheng Yan

The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.

Visual Question Answering

Faithful Logical Reasoning via Symbolic Chain-of-Thought

1 code implementation28 May 2024 Jundong Xu, Hao Fei, Liangming Pan, Qian Liu, Mong-Li Lee, Wynne Hsu

Technically, building upon an LLM, SymbCoT 1) first translates the natural language context into the symbolic format, and then 2) derives a step-by-step plan to solve the problem with symbolic logical rules, 3) followed by a verifier to check the translation and reasoning chain.

Logical Reasoning

ProtT3: Protein-to-Text Generation for Text-based Protein Understanding

1 code implementation21 May 2024 Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua

ProtT3 empowers an LM to understand protein sequences of amino acids by incorporating a PLM as its protein understanding module, enabling effective protein-to-text generation.

Property Prediction Question Answering +2

Modeling Unified Semantic Discourse Structure for High-quality Headline Generation

no code implementations23 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.

Headline Generation Sentence

In-Context Learning for Few-Shot Nested Named Entity Recognition

no code implementations2 Feb 2024 Meishan Zhang, Bin Wang, Hao Fei, Min Zhang

In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address.

Contrastive Learning In-Context Learning +7

Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correction

no code implementations28 Jan 2024 Kangkang Lu, Yanhua Yu, Hao Fei, Xuan Li, Zixuan Yang, Zirui Guo, Meiyu Liang, Mengran Yin, Tat-Seng Chua

Moreover, we theoretically establish that the number of distinguishable eigenvalues plays a pivotal role in determining the expressive power of spectral graph neural networks.

Node Classification

Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought

1 code implementation23 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.

Question Answering

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning

1 code implementation30 Nov 2023 Sijin Chen, Xin Chen, Chi Zhang, Mingsheng Li, Gang Yu, Hao Fei, Hongyuan Zhu, Jiayuan Fan, Tao Chen

However, developing LMMs that can comprehend, reason, and plan in complex and diverse 3D environments remains a challenging topic, especially considering the demand for understanding permutation-invariant point cloud 3D representations of the 3D scene.

3D dense captioning Dense Captioning +1

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback

no code implementations21 Nov 2023 Minghe Gao, Juncheng Li, Hao Fei, Liang Pang, Wei Ji, Guoming Wang, Wenqiao Zhang, Siliang Tang, Yueting Zhuang

Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks.

Logical Reasoning

Towards Complex-query Referring Image Segmentation: A Novel Benchmark

no code implementations29 Sep 2023 Wei Ji, Li Li, Hao Fei, Xiangyan Liu, Xun Yang, Juncheng Li, Roger Zimmermann

Referring Image Understanding (RIS) has been extensively studied over the past decade, leading to the development of advanced algorithms.

Image Segmentation Semantic Segmentation

NExT-GPT: Any-to-Any Multimodal LLM

1 code implementation11 Sep 2023 Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, Tat-Seng Chua

While recently Multimodal Large Language Models (MM-LLMs) have made exciting strides, they mostly fall prey to the limitation of only input-side multimodal understanding, without the ability to produce content in multiple modalities.

AI Agent

I3: Intent-Introspective Retrieval Conditioned on Instructions

no code implementations19 Aug 2023 Kaihang Pan, Juncheng Li, Wenjie Wang, Hao Fei, Hongye Song, Wei Ji, Jun Lin, Xiaozhong Liu, Tat-Seng Chua, Siliang Tang

Recent studies indicate that dense retrieval models struggle to perform well on a wide variety of retrieval tasks that lack dedicated training data, as different retrieval tasks often entail distinct search intents.

Retrieval Text-to-Image Generation

LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation

no code implementations9 Aug 2023 Leigang Qu, Shengqiong Wu, Hao Fei, Liqiang Nie, Tat-Seng Chua

Afterward, we propose a fine-grained object-interaction diffusion method to synthesize high-faithfulness images conditioned on the prompt and the automatically generated layout.

In-Context Learning Text-to-Image Generation

Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling

no code implementations9 Aug 2023 Yu Zhao, Hao Fei, Yixin Cao, Bobo Li, Meishan Zhang, Jianguo Wei, Min Zhang, Tat-Seng Chua

A scene-event mapping mechanism is first designed to bridge the gap between the underlying scene structure and the high-level event semantic structure, resulting in an overall hierarchical scene-event (termed ICE) graph structure.

Semantic Role Labeling

Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition

no code implementations8 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.

Contrastive Learning Disentanglement +2

DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs

no code implementations8 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.

coreference-resolution Relation Extraction

XNLP: An Interactive Demonstration System for Universal Structured NLP

no code implementations3 Aug 2023 Hao Fei, Meishan Zhang, Min Zhang, Tat-Seng Chua

Structured Natural Language Processing (XNLP) is an important subset of NLP that entails understanding the underlying semantic or syntactic structure of texts, which serves as a foundational component for many downstream applications.

ECQED: Emotion-Cause Quadruple Extraction in Dialogs

no code implementations6 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.

Emotion-Cause Pair Extraction

Revisiting Conversation Discourse for Dialogue Disentanglement

no code implementations6 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.

Attribute Disentanglement

Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment

no code implementations20 May 2023 Shengqiong Wu, Hao Fei, Wei Ji, Tat-Seng Chua

Unpaired cross-lingual image captioning has long suffered from irrelevancy and disfluency issues, due to the inconsistencies of the semantic scene and syntax attributes during transfer.

Image Captioning Translation

Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction

no code implementations20 May 2023 Hao Fei, Meishan Zhang, Min Zhang, Tat-Seng Chua

Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e. g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages.

Relation Relation Extraction +1

Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination

1 code implementation20 May 2023 Hao Fei, Qian Liu, Meishan Zhang, Min Zhang, Tat-Seng Chua

In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs.

Hallucination Multimodal Machine Translation +1

Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling

1 code implementation19 May 2023 Shengqiong Wu, Hao Fei, Yixin Cao, Lidong Bing, Tat-Seng Chua

First, we represent the fine-grained semantic structures of the input image and text with the visual and textual scene graphs, which are further fused into a unified cross-modal graph (CMG).

Denoising Relation +1

Generating Visual Spatial Description via Holistic 3D Scene Understanding

1 code implementation19 May 2023 Yu Zhao, Hao Fei, Wei Ji, Jianguo Wei, Meishan Zhang, Min Zhang, Tat-Seng Chua

With an external 3D scene extractor, we obtain the 3D objects and scene features for input images, based on which we construct a target object-centered 3D spatial scene graph (Go3D-S2G), such that we model the spatial semantics of target objects within the holistic 3D scenes.

Scene Understanding Text Generation

Reasoning Implicit Sentiment with Chain-of-Thought Prompting

2 code implementations18 May 2023 Hao Fei, Bobo Li, Qian Liu, Lidong Bing, Fei Li, Tat-Seng Chua

While sentiment analysis systems try to determine the sentiment polarities of given targets based on the key opinion expressions in input texts, in implicit sentiment analysis (ISA) the opinion cues come in an implicit and obscure manner.

Common Sense Reasoning Sentiment Analysis

VPGTrans: Transfer Visual Prompt Generator across LLMs

1 code implementation NeurIPS 2023 Ao Zhang, Hao Fei, Yuan YAO, Wei Ji, Li Li, Zhiyuan Liu, Tat-Seng Chua

While developing a new multimodal LLM (MLLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm.

Transfer Learning

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

no code implementations19 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

LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model

1 code implementation13 Apr 2023 Hao Fei, Shengqiong Wu, Jingye Li, Bobo Li, Fei Li, Libo Qin, Meishan Zhang, Min Zhang, Tat-Seng Chua

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 predictions are unified into a linearized hierarchical expression under a GLM.

Language Modelling UIE

Entity-centered Cross-document Relation Extraction

2 code implementations29 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 Relation Extraction +1

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 Relation

Global inference with explicit syntactic and discourse structures for dialogue-level relation extraction

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.

Dialog Relation Extraction Relation +1

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.

Aspect Sentiment Triplet Extraction Decoder

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.

 Ranked #1 on Fine-Grained Opinion Analysis on MPQA (F1 (Opinion) metric)

Fine-Grained Opinion Analysis

Encoder-decoder based unified semantic role labeling with label-aware syntax

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.

Decoder Semantic Role Labeling

Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer Networks

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.

Boundary Detection Decoder +3

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.

Sentence

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

no code implementations19 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.

Clustering

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

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

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.