Search Results for author: Zhixu Li

Found 43 papers, 22 papers with code

Tackling Zero Pronoun Resolution and Non-Zero Coreference Resolution Jointly

1 code implementation CoNLL (EMNLP) 2021 Shisong Chen, Binbin Gu, Jianfeng Qu, Zhixu Li, An Liu, Lei Zhao, Zhigang Chen

Zero pronoun resolution aims at recognizing dropped pronouns and pointing out their anaphoric mentions, while non-zero coreference resolution targets at clustering mentions referring to the same entity.

coreference-resolution

Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance

no code implementations24 Feb 2025 Chenghua Huang, Lu Wang, Fangkai Yang, Pu Zhao, Zhixu Li, QIngwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

Proximal Policy Optimization (PPO)-based Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models (LLMs) with human preferences.

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

1 code implementation14 Oct 2024 Xiangru Zhu, Penglei Sun, Yaoxian Song, Yanghua Xiao, Zhixu Li, Chengyu Wang, Jun Huang, Bei Yang, Xiaoxiao Xu

To address these deficiencies, we propose a novel metric called SemVarEffect and a benchmark named SemVarBench, designed to evaluate the causality between semantic variations in inputs and outputs in T2I synthesis.

cross-modal alignment Image Generation

HOTVCOM: Generating Buzzworthy Comments for Videos

no code implementations23 Sep 2024 Yuyan Chen, Yiwen Qian, Songzhou Yan, Jiyuan Jia, Zhixu Li, Yanghua Xiao, Xiaobo Li, Ming Yang, Qingpei Guo

In the era of social media video platforms, popular ``hot-comments'' play a crucial role in attracting user impressions of short-form videos, making them vital for marketing and branding purpose.

Descriptive Marketing

Incorporating Like-Minded Peers to Overcome Friend Data Sparsity in Session-Based Social Recommendations

no code implementations4 Sep 2024 Chunyan An, Yunhan Li, Qiang Yang, Winston K. G. Seah, Zhixu Li, Conghao Yang

This approach not only alleviates the problem of friend data sparsity but also effectively incorporates users with similar preferences to the target user.

Graph Attention Session-Based Recommendations

XMeCap: Meme Caption Generation with Sub-Image Adaptability

no code implementations24 Jul 2024 Yuyan Chen, Songzhou Yan, Zhihong Zhu, Zhixu Li, Yanghua Xiao

Humor, deeply rooted in societal meanings and cultural details, poses a unique challenge for machines.

Caption Generation Meme Captioning

Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models

no code implementations4 Jul 2024 Yuyan Chen, Qiang Fu, Yichen Yuan, Zhihao Wen, Ge Fan, Dayiheng Liu, Dongmei Zhang, Zhixu Li, Yanghua Xiao

Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems.

Hallucination Question Answering

Can Pre-trained Language Models Understand Chinese Humor?

no code implementations4 Jul 2024 Yuyan Chen, Zhixu Li, Jiaqing Liang, Yanghua Xiao, Bang Liu, Yunwen Chen

Humor understanding is an important and challenging research in natural language processing.

MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization

no code implementations4 Jul 2024 Yuyan Chen, Zhihao Wen, Ge Fan, Zhengyu Chen, Wei Wu, Dayiheng Liu, Zhixu Li, Bang Liu, Yanghua Xiao

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community.

Language Modeling Language Modelling +3

Multi-Task Domain Adaptation for Language Grounding with 3D Objects

no code implementations3 Jul 2024 Penglei Sun, Yaoxian Song, Xinglin Pan, Peijie Dong, Xiaofei Yang, Qiang Wang, Zhixu Li, Tiefeng Li, Xiaowen Chu

However, they have failed to consider exploring the cross-modal representation of language-vision alignment in the cross-domain field.

Domain Adaptation Multi-Task Learning

ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models

3 code implementations21 Jun 2024 Haiquan Zhao, Lingyu Li, Shisong Chen, Shuqi Kong, Jiaan Wang, Kexin Huang, Tianle Gu, Yixu Wang, Wang Jian, Dandan Liang, Zhixu Li, Yan Teng, Yanghua Xiao, Yingchun Wang

Inspired by the awesome development of role-playing agents, we propose an ESC Evaluation framework (ESC-Eval), which uses a role-playing agent to interact with ESC models, followed by a manual evaluation of the interactive dialogues.

SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration

1 code implementation19 Jun 2024 Jipeng Cen, Jiaxin Liu, Zhixu Li, Jingjing Wang

Subsequently, leveraging similar repair retrieval and failure memory reflection, the SQLRefiner agent selects the most fitting SQL statement from the candidates as the final repair.

SQL Parsing Text-To-SQL +1

VCEval: Rethinking What is a Good Educational Video and How to Automatically Evaluate It

no code implementations15 Jun 2024 Xiaoxuan Zhu, Zhouhong Gu, Sihang Jiang, Zhixu Li, Hongwei Feng, Yanghua Xiao

Online courses have significantly lowered the barrier to accessing education, yet the varying content quality of these videos poses challenges.

Language Modeling Language Modelling +2

AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation

2 code implementations19 Apr 2024 Wenhao Huang, Zhouhong Gu, Chenghao Peng, Zhixu Li, Jiaqing Liang, Yanghua Xiao, Liqian Wen, Zulong Chen

In this work, we introduce the paradigm of generating web scrapers with LLMs and propose AutoScraper, a two-stage framework that can handle diverse and changing web environments more efficiently.

Action Generation

OVEL: Large Language Model as Memory Manager for Online Video Entity Linking

no code implementations3 Mar 2024 Haiquan Zhao, Xuwu Wang, Shisong Chen, Zhixu Li, Xin Zheng, Yanghua Xiao

In this paper, we propose a task called Online Video Entity Linking OVEL, aiming to establish connections between mentions in online videos and a knowledge base with high accuracy and timeliness.

Entity Linking Language Modeling +3

Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning

1 code implementation9 Jan 2024 Jiaan Wang, Jianfeng Qu, Kexin Wang, Zhixu Li, Wen Hua, Ximing Li, An Liu

Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\emph{e. g.}, knowledge graphs; KGs).

Contrastive Learning Knowledge Graphs

M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base

1 code implementation16 Dec 2023 Zhiwei Zha, Jiaan Wang, Zhixu Li, Xiangru Zhu, Wei Song, Yanghua Xiao

Comprising 951K images and 152K concepts, M^2ConceptBase links each concept to an average of 6. 27 images and a single description, ensuring comprehensive visual and textual semantics.

cross-modal alignment Knowledge Graphs +2

AspectMMKG: A Multi-modal Knowledge Graph with Aspect-aware Entities

1 code implementation9 Aug 2023 Jingdan Zhang, Jiaan Wang, Xiaodan Wang, Zhixu Li, Yanghua Xiao

Multi-modal knowledge graphs (MMKGs) combine different modal data (e. g., text and image) for a comprehensive understanding of entities.

Extract Aspect Image Retrieval +2

Snowman: A Million-scale Chinese Commonsense Knowledge Graph Distilled from Foundation Model

no code implementations17 Jun 2023 Jiaan Wang, Jianfeng Qu, Yunlong Liang, Zhixu Li, An Liu, Guanfeng Liu, Xin Zheng

Constructing commonsense knowledge graphs (CKGs) has attracted wide research attention due to its significant importance in cognitive intelligence.

Knowledge Graphs

Towards Unifying Multi-Lingual and Cross-Lingual Summarization

no code implementations16 May 2023 Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie zhou

In this paper, we aim to unify MLS and CLS into a more general setting, i. e., many-to-many summarization (M2MS), where a single model could process documents in any language and generate their summaries also in any language.

Language Modeling Language Modelling +1

GANTEE: Generative Adversatial Network for Taxonomy Entering Evaluation

no code implementations25 Mar 2023 Zhouhong Gu, Sihang Jiang, Jingping Liu, Yanghua Xiao, Hongwei Feng, Zhixu Li, Jiaqing Liang, Jian Zhong

The previous methods suffer from low-efficiency since they waste much time when most of the new coming concepts are indeed noisy concepts.

Generative Adversarial Network Taxonomy Expansion

Is ChatGPT a Good NLG Evaluator? A Preliminary Study

1 code implementation7 Mar 2023 Jiaan Wang, Yunlong Liang, Fandong Meng, Zengkui Sun, Haoxiang Shi, Zhixu Li, Jinan Xu, Jianfeng Qu, Jie zhou

In detail, we regard ChatGPT as a human evaluator and give task-specific (e. g., summarization) and aspect-specific (e. g., relevance) instruction to prompt ChatGPT to evaluate the generated results of NLG models.

nlg evaluation Story Generation

Zero-Shot Cross-Lingual Summarization via Large Language Models

no code implementations28 Feb 2023 Jiaan Wang, Yunlong Liang, Fandong Meng, Beiqi Zou, Zhixu Li, Jianfeng Qu, Jie zhou

Given a document in a source language, cross-lingual summarization (CLS) aims to generate a summary in a different target language.

Informativeness

Learning 6-DoF Fine-grained Grasp Detection Based on Part Affordance Grounding

no code implementations27 Jan 2023 Yaoxian Song, Penglei Sun, Piaopiao Jin, Yi Ren, Yu Zheng, Zhixu Li, Xiaowen Chu, Yue Zhang, Tiefeng Li, Jason Gu

From the perspective of robotic cognition, we design a two-stage fine-grained robotic grasping framework (named LangPartGPD), including a novel 3D part language grounding model and a part-aware grasp pose detection model, in which explicit language input from human or large language models (LLMs) could guide a robot to generate part-level 6-DoF grasping pose with textual explanation.

3D geometry Representation Learning +1

Understanding Translationese in Cross-Lingual Summarization

no code implementations14 Dec 2022 Jiaan Wang, Fandong Meng, Yunlong Liang, Tingyi Zhang, Jiarong Xu, Zhixu Li, Jie zhou

In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation; (2) the translationese in training sets would harm model performance in real-world applications; (3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies.

Long-Document Cross-Lingual Summarization

1 code implementation1 Dec 2022 Shaohui Zheng, Zhixu Li, Jiaan Wang, Jianfeng Qu, An Liu, Lei Zhao, Zhigang Chen

Cross-Lingual Summarization (CLS) aims at generating summaries in one language for the given documents in another language.

Machine Translation

Generative Entity Typing with Curriculum Learning

1 code implementation6 Oct 2022 Siyu Yuan, Deqing Yang, Jiaqing Liang, Zhixu Li, Jinxi Liu, Jingyue Huang, Yanghua Xiao

To overcome these drawbacks, we propose a novel generative entity typing (GET) paradigm: given a text with an entity mention, the multiple types for the role that the entity plays in the text are generated with a pre-trained language model (PLM).

Entity Typing Language Modelling

RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation

1 code implementation17 Jul 2022 Kexin Wang, Zhixu Li, Jiaan Wang, Jianfeng Qu, Ying He, An Liu, Lei Zhao

Nevertheless, the correlations between knowledge implied in the multi-turn context and the transition regularities between relations in KGs are under-explored.

Dialogue Generation Knowledge Graphs +2

WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types

3 code implementations ACL 2022 Xuwu Wang, Junfeng Tian, Min Gui, Zhixu Li, Rui Wang, Ming Yan, Lihan Chen, Yanghua Xiao

In this paper, we present WikiDiverse, a high-quality human-annotated MEL dataset with diversified contextual topics and entity types from Wikinews, which uses Wikipedia as the corresponding knowledge base.

Entity Linking

A Survey on Cross-Lingual Summarization

no code implementations23 Mar 2022 Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie zhou

Cross-lingual summarization is the task of generating a summary in one language (e. g., English) for the given document(s) in a different language (e. g., Chinese).

Survey

Can Pre-trained Language Models Interpret Similes as Smart as Human?

1 code implementation ACL 2022 Qianyu He, Sijie Cheng, Zhixu Li, Rui Xie, Yanghua Xiao

In this paper, we investigate the ability of PLMs in simile interpretation by designing a novel task named Simile Property Probing, i. e., to let the PLMs infer the shared properties of similes.

Sentiment Analysis Sentiment Classification

ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization

2 code implementations11 Feb 2022 Jiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng, Zhixu Li, Jianfeng Qu, Jie zhou

We present ClidSum, a benchmark dataset for building cross-lingual summarization systems on dialogue documents.

Multi-Modal Knowledge Graph Construction and Application: A Survey

no code implementations11 Feb 2022 Xiangru Zhu, Zhixu Li, Xiaodan Wang, Xueyao Jiang, Penglei Sun, Xuwu Wang, Yanghua Xiao, Nicholas Jing Yuan

In this survey on MMKGs constructed by texts and images, we first give definitions of MMKGs, followed with the preliminaries on multi-modal tasks and techniques.

graph construction Knowledge Graphs +2

Incorporating Commonsense Knowledge into Story Ending Generation via Heterogeneous Graph Networks

1 code implementation29 Jan 2022 Jiaan Wang, Beiqi Zou, Zhixu Li, Jianfeng Qu, Pengpeng Zhao, An Liu, Lei Zhao

Story ending generation is an interesting and challenging task, which aims to generate a coherent and reasonable ending given a story context.

Multi-Task Learning

Knowledge Enhanced Sports Game Summarization

1 code implementation24 Nov 2021 Jiaan Wang, Zhixu Li, Tingyi Zhang, Duo Zheng, Jianfeng Qu, An Liu, Lei Zhao, Zhigang Chen

Additionally, we also introduce a knowledge-enhanced summarizer that utilizes both live commentaries and the knowledge to generate sports news.

Multi-Modal Chorus Recognition for Improving Song Search

1 code implementation27 Jun 2021 Jiaan Wang, Zhixu Li, Binbin Gu, Tingyi Zhang, Qingsheng Liu, Zhigang Chen

In addition, our approach also helps to improve the accuracy of its downstream task - song search by more than 10. 6%.

Overcoming Data Sparsity in Group Recommendation

no code implementations2 Oct 2020 Hongzhi Yin, Qinyong Wang, Kai Zheng, Zhixu Li, Xiaofang Zhou

Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members.

Decision Making Graph Embedding +2

Where to Go Next: A Spatio-temporal LSTM model for Next POI Recommendation

no code implementations18 Jun 2018 Pengpeng Zhao, Haifeng Zhu, Yanchi Liu, Zhixu Li, Jiajie Xu, Victor S. Sheng

Furthermore, to reduce the number of parameters and improve efficiency, we further integrate coupled input and forget gates with our proposed model.

Sequential Recommendation

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