Search Results for author: Shengqiong Wu

Found 23 papers, 13 papers with code

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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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