Search Results for author: Kam-Fai Wong

Found 82 papers, 21 papers with code

A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition

no code implementations EMNLP 2021 Huimin Wang, Kam-Fai Wong

Most reinforcement learning methods for dialog policy learning train a centralized agent that selects a predefined joint action concatenating domain name, intent type, and slot name.

Multi-agent Reinforcement Learning reinforcement-learning +1

Visually Guided Generative Text-Layout Pre-training for Document Intelligence

1 code implementation25 Mar 2024 Zhiming Mao, Haoli Bai, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu, Kam-Fai Wong

Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e. g., locations of texts and table-cells).

Document Classification document understanding +2

Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models

no code implementations5 Mar 2024 Rui Wang, Fei Mi, Yi Chen, Boyang Xue, Hongru Wang, Qi Zhu, Kam-Fai Wong, Ruifeng Xu

2) Role Prompting assigns a central prompt to the general domain and a unique role prompt to each specific domain to minimize inter-domain confusion during training.

Domain Adaptation

UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval

no code implementations26 Feb 2024 Hongru Wang, Boyang Xue, Baohang Zhou, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Kam-Fai Wong

Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively engage with the user and successfully complete the dialogue.

Information Retrieval Retrieval

COPR: Continual Human Preference Learning via Optimal Policy Regularization

no code implementations22 Feb 2024 Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Yulan He, Hui Wang, Yue Yu, Kam-Fai Wong, Bin Liang, Ruifeng Xu

Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences.

Continual Learning

Multi-modal Stance Detection: New Datasets and Model

no code implementations22 Feb 2024 Bin Liang, Ang Li, Jingqian Zhao, Lin Gui, Min Yang, Yue Yu, Kam-Fai Wong, Ruifeng Xu

Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets.

Stance Detection

Self-DC: When to retrieve and When to generate? Self Divide-and-Conquer for Compositional Unknown Questions

no code implementations21 Feb 2024 Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang, Cunxiang Wang, Guanhua Chen, Huimin Wang, Kam-Fai Wong

Retrieve-then-read and generate-then-read are two typical solutions to handle unknown and known questions in open-domain question-answering, while the former retrieves necessary external knowledge and the later prompt the large language models to generate internal known knowledge encoded in the parameters.

Binary Classification Open-Domain Question Answering +1

A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models

no code implementations21 Feb 2024 Boyang Xue, Hongru Wang, Weichao Wang, Rui Wang, Sheng Wang, Zeming Liu, Kam-Fai Wong

The tendency of Large Language Models to generate hallucinations and exhibit overconfidence in predictions raises concerns regarding their reliability.

Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models

no code implementations8 Feb 2024 Lingzhi Wang, Xingshan Zeng, Jinsong Guo, Kam-Fai Wong, Georg Gottlob

The aim of this study is to investigate Machine Unlearning (MU), a burgeoning field focused on addressing concerns related to neural models inadvertently retaining personal or sensitive data.

Computational Efficiency Language Modelling +1

IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators

no code implementations1 Feb 2024 Luyang Lin, Lingzhi Wang, Xiaoyan Zhao, Jing Li, Kam-Fai Wong

IndiVec begins by constructing a fine-grained media bias database, leveraging the robust instruction-following capabilities of large language models and vector database techniques.

Bias Detection Instruction Following

MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models

1 code implementation30 Jan 2024 Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, YuFei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications.

UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems

no code implementations24 Jan 2024 Hongru Wang, WenYu Huang, Yang Deng, Rui Wang, Zezhong Wang, YuFei Wang, Fei Mi, Jeff Z. Pan, Kam-Fai Wong

To better plan and incorporate the use of multiple sources in generating personalized response, we firstly decompose it into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation.

Response Generation Retrieval

A Survey of the Evolution of Language Model-Based Dialogue Systems

no code implementations28 Nov 2023 Hongru Wang, Lingzhi Wang, Yiming Du, Liang Chen, Jingyan Zhou, YuFei Wang, Kam-Fai Wong

This survey delves into the historical trajectory of dialogue systems, elucidating their intricate relationship with advancements in language models by categorizing this evolution into four distinct stages, each marked by pivotal LM breakthroughs: 1) Early_Stage: characterized by statistical LMs, resulting in rule-based or machine-learning-driven dialogue_systems; 2) Independent development of TOD and ODD based on neural_language_models (NLM; e. g., LSTM and GRU), since NLMs lack intrinsic knowledge in their parameters; 3) fusion between different types of dialogue systems with the advert of pre-trained_language_models (PLMs), starting from the fusion between four_sub-tasks_within_TOD, and then TOD_with_ODD; and 4) current LLM-based_dialogue_system, wherein LLMs can be used to conduct TOD and ODD seamlessly.

Language Modelling

Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue

no code implementations13 Oct 2023 Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses.

Response Generation

Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment

1 code implementation12 Oct 2023 Boyang Xue, Weichao Wang, Hongru Wang, Fei Mi, Rui Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

Inspired by previous work which identified that feed-forward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability {of FFNs} by knowledge enhancement and alignment respectively.

Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators

1 code implementation11 Oct 2023 Liang Chen, Yang Deng, Yatao Bian, Zeyu Qin, Bingzhe Wu, Tat-Seng Chua, Kam-Fai Wong

Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge.

Information Retrieval Informativeness +4

TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaboration

no code implementations28 Sep 2023 Hongru Wang, Huimin Wang, Lingzhi Wang, Minda Hu, Rui Wang, Boyang Xue, Hongyuan Lu, Fei Mi, Kam-Fai Wong

Large language models (LLMs) have demonstrated exceptional performance in planning the use of various functional tools, such as calculators and retrievers, particularly in question-answering tasks.

Question Answering Response Generation

Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices

no code implementations5 Sep 2023 Bojia Zi, Xianbiao Qi, Lingzhi Wang, Jianan Wang, Kam-Fai Wong, Lei Zhang

In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs).

Dialog Action-Aware Transformer for Dialog Policy Learning

no code implementations5 Sep 2023 Huimin Wang, Wai-Chung Kwan, Kam-Fai Wong

Recent works usually address Dialog policy learning DPL by training a reinforcement learning (RL) agent to determine the best dialog action.

Language Modelling Reinforcement Learning (RL)

JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning

1 code implementation1 Sep 2023 Wai-Chung Kwan, Huimin Wang, Hongru Wang, Zezhong Wang, Xian Wu, Yefeng Zheng, Kam-Fai Wong

In addition, JoTR employs reinforcement learning with a reward-shaping mechanism to efficiently finetune the word-level dialogue policy, which allows the model to learn from its interactions, improving its performance over time.

Action Generation

CoAD: Automatic Diagnosis through Symptom and Disease Collaborative Generation

1 code implementation17 Jul 2023 Huimin Wang, Wai-Chung Kwan, Kam-Fai Wong, Yefeng Zheng

Automatic diagnosis (AD), a critical application of AI in healthcare, employs machine learning techniques to assist doctors in gathering patient symptom information for precise disease diagnosis.

Disease Prediction Sentence

UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation

1 code implementation25 May 2023 Zhiming Mao, Huimin Wang, Yiming Du, Kam-Fai Wong

Moreover, conditioned on user history encoded by Transformer encoders, our framework leverages Transformer decoders to estimate the language perplexity of candidate text items, which can serve as a straightforward yet significant contrastive signal for user-item text matching.

Contrastive Learning Text Matching

Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting

1 code implementation23 May 2023 Rui Wang, Hongru Wang, Fei Mi, Yi Chen, Boyang Xue, Kam-Fai Wong, Ruifeng Xu

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful.

counterfactual Fact Checking

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

2 code implementations19 May 2023 Hongru Wang, Rui Wang, Fei Mi, Yang Deng, Zezhong Wang, Bin Liang, Ruifeng Xu, Kam-Fai Wong

Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities.

Question Answering Semantic Similarity +1

KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment

1 code implementation11 May 2023 Lingzhi Wang, Tong Chen, Wei Yuan, Xingshan Zeng, Kam-Fai Wong, Hongzhi Yin

Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed in the training set.

Machine Unlearning Response Generation

Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation

no code implementations27 Feb 2023 Lingzhi Wang, Mrinmaya Sachan, Xingshan Zeng, Kam-Fai Wong

Conversational tutoring systems (CTSs) aim to help students master educational material with natural language interaction in the form of a dialog.

Response Generation

DIGAT: Modeling News Recommendation with Dual-Graph Interaction

1 code implementation11 Oct 2022 Zhiming Mao, Jian Li, Hongru Wang, Xingshan Zeng, Kam-Fai Wong

Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal.

Graph Attention News Recommendation +1

Improving Conversational Recommender System via Contextual and Time-Aware Modeling with Less Domain-Specific Knowledge

no code implementations23 Sep 2022 Lingzhi Wang, Shafiq Joty, Wei Gao, Xingshan Zeng, Kam-Fai Wong

In addition to conducting experiments on a popular dataset (ReDial), we also include a multi-domain dataset (OpenDialKG) to show the effectiveness of our model.

Recommendation Systems

Integrating Pretrained Language Model for Dialogue Policy Learning

no code implementations2 Nov 2021 Hongru Wang, Huimin Wang, Zezhong Wang, Kam-Fai Wong

Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users.

Language Modelling Reinforcement Learning (RL)

RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models

no code implementations14 Oct 2021 Lingzhi Wang, Huang Hu, Lei Sha, Can Xu, Kam-Fai Wong, Daxin Jiang

Furthermore, we propose to evaluate the CRS models in an end-to-end manner, which can reflect the overall performance of the entire system rather than the performance of individual modules, compared to the separate evaluations of the two modules used in previous work.

Dialogue Generation Language Modelling +1

Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning

no code implementations13 Oct 2021 Hongru Wang, Zhijing Jin, Jiarun Cao, Gabriel Pui Cheong Fung, Kam-Fai Wong

However, previous works rarely investigate the effects of a different number of classes (i. e., $N$-way) and number of labeled data per class (i. e., $K$-shot) during training vs. testing.

Contrastive Learning Few-Shot Relation Classification +1

TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System

no code implementations11 Sep 2021 Hongru Wang, Mingyu Cui, Zimo Zhou, Gabriel Pui Cheong Fung, Kam-Fai Wong

A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware responses.

Response Generation

Neural News Recommendation with Collaborative News Encoding and Structural User Encoding

1 code implementation Findings (EMNLP) 2021 Zhiming Mao, Xingshan Zeng, Kam-Fai Wong

In this work, we propose a news recommendation framework consisting of collaborative news encoding (CNE) and structural user encoding (SUE) to enhance news and user representation learning.

News Recommendation Reading Comprehension +1

Quotation Recommendation and Interpretation Based on Transformation from Queries to Quotations

1 code implementation ACL 2021 Lingzhi Wang, Xingshan Zeng, Kam-Fai Wong

To help individuals express themselves better, quotation recommendation is receiving growing attention.

KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System

no code implementations17 Nov 2020 Hongru Wang, Min Li, Zimo Zhou, Gabriel Pui Cheong Fung, Kam-Fai Wong

In this paper, we publish a first Cantonese knowledge-driven Dialogue Dataset for REStaurant (KddRES) in Hong Kong, which grounds the information in multi-turn conversations to one specific restaurant.

Learning Efficient Dialogue Policy from Demonstrations through Shaping

no code implementations ACL 2020 Huimin Wang, Baolin Peng, Kam-Fai Wong

Training a task-oriented dialogue agent with reinforcement learning is prohibitively expensive since it requires a large volume of interactions with users.

Domain Adaptation

Dynamic Online Conversation Recommendation

no code implementations ACL 2020 Xingshan Zeng, Jing Li, Lu Wang, Zhiming Mao, Kam-Fai Wong

Trending topics in social media content evolve over time, and it is therefore crucial to understand social media users and their interpersonal communications in a dynamic manner.

Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition

no code implementations NAACL 2021 Dingmin Wang, Chenghua Lin, Qi Liu, Kam-Fai Wong

We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states.

Classification Dialogue State Tracking +3

Neural Conversation Recommendation with Online Interaction Modeling

no code implementations IJCNLP 2019 Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong

The prevalent use of social media leads to a vast amount of online conversations being produced on a daily basis.

Collaborative Filtering

Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks

no code implementations ACL 2019 Jing Ma, Wei Gao, Shafiq Joty, Kam-Fai Wong

Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications.

Claim Verification Sentence

Joint Effects of Context and User History for Predicting Online Conversation Re-entries

1 code implementation ACL 2019 Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong

We hypothesize that both the context of the ongoing conversations and the users' previous chatting history will affect their continued interests in future engagement.

A Joint Model of Conversational Discourse Latent Topics on Microblogs

no code implementations CL 2018 Jing Li, Yan Song, Zhongyu Wei, Kam-Fai Wong

To address this issue, we organize microblog messages as conversation trees based on their reposting and replying relations, and propose an unsupervised model that jointly learns word distributions to represent: (1) different roles of conversational discourse, and (2) various latent topics in reflecting content information.

Topic Models

A Joint Model of Conversational Discourse and Latent Topics on Microblogs

no code implementations11 Sep 2018 Jing Li, Yan Song, Zhongyu Wei, Kam-Fai Wong

To address this issue, we organize microblog messages as conversation trees based on their reposting and replying relations, and propose an unsupervised model that jointly learns word distributions to represent: 1) different roles of conversational discourse, 2) various latent topics in reflecting content information.

Topic Models

Microblog Conversation Recommendation via Joint Modeling of Topics and Discourse

no code implementations NAACL 2018 Xingshan Zeng, Jing Li, Lu Wang, Nicholas Beauchamp, Sarah Shugars, Kam-Fai Wong

We propose a statistical model that jointly captures: (1) topics for representing user interests and conversation content, and (2) discourse modes for describing user replying behavior and conversation dynamics.

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

3 code implementations ACL 2018 Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su

During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience.

Reinforcement Learning (RL) Task-Completion Dialogue Policy Learning

IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases

no code implementations IJCNLP 2017 Liang-Chih Yu, Lung-Hao Lee, Jin Wang, Kam-Fai Wong

This paper presents the IJCNLP 2017 shared task on Dimensional Sentiment Analysis for Chinese Phrases (DSAP) which seeks to identify a real-value sentiment score of Chinese single words and multi-word phrases in the both valence and arousal dimensions.

Sentiment Analysis Task 2

NLPTEA 2017 Shared Task -- Chinese Spelling Check

no code implementations WS 2017 Gabriel Fung, Maxime Debosschere, Dingmin Wang, Bo Li, Jia Zhu, Kam-Fai Wong

This paper provides an overview along with our findings of the Chinese Spelling Check shared task at NLPTEA 2017.

Sentence

Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning

no code implementations31 Oct 2017 Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen, Kam-Fai Wong

This paper presents a new method --- adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems.

Task-Completion Dialogue Policy Learning

An Attentional Neural Conversation Model with Improved Specificity

no code implementations3 Jun 2016 Kaisheng Yao, Baolin Peng, Geoffrey Zweig, Kam-Fai Wong

Experimental results indicate that the model outperforms previously proposed neural conversation architectures, and that using specificity in the objective function significantly improves performances for both generation and retrieval.

Retrieval Specificity

Towards Neural Network-based Reasoning

1 code implementation22 Aug 2015 Baolin Peng, Zhengdong Lu, Hang Li, Kam-Fai Wong

For example, it improves the accuracy on Path Finding(10K) from 33. 4% [6] to over 98%.

Quantising Opinions for Political Tweets Analysis

no code implementations LREC 2012 Yulan He, Hassan Saif, Zhongyu Wei, Kam-Fai Wong

There have been increasing interests in recent years in analyzing tweet messages relevant to political events so as to understand public opinions towards certain political issues.

Sentiment Analysis

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