Search Results for author: Wenxuan Zhang

Found 54 papers, 38 papers with code

AnswerFact: Fact Checking in Product Question Answering

no code implementations EMNLP 2020 Wenxuan Zhang, Yang Deng, Jing Ma, Wai Lam

Product-related question answering platforms nowadays are widely employed in many E-commerce sites, providing a convenient way for potential customers to address their concerns during online shopping.

Fact Checking Misinformation +1

Aspect-based Sentiment Analysis in Question Answering Forums

1 code implementation Findings (EMNLP) 2021 Wenxuan Zhang, Yang Deng, Xin Li, Lidong Bing, Wai Lam

This motivates us to investigate the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models

no code implementations15 Mar 2024 Chaoqun Liu, Wenxuan Zhang, Yiran Zhao, Anh Tuan Luu, Lidong Bing

We find that even though translation into English can help improve the performance of multilingual NLP tasks for English-centric LLMs, it may not be optimal for all scenarios.

Multilingual NLP

AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging

1 code implementation29 Feb 2024 Yiran Zhao, Wenxuan Zhang, Huiming Wang, Kenji Kawaguchi, Lidong Bing

In this paper, we acknowledge the mutual reliance between task ability and language ability and direct our attention toward the gap between the target language and the source language on tasks.

Cross-Lingual Transfer

How do Large Language Models Handle Multilingualism?

no code implementations29 Feb 2024 Yiran Zhao, Wenxuan Zhang, Guizhen Chen, Kenji Kawaguchi, Lidong Bing

We introduce a framework that depicts LLMs' processing of multilingual inputs: In the first several layers, LLMs understand the question, converting multilingual inputs into English to facilitate the task-solving phase.

On the Multi-turn Instruction Following for Conversational Web Agents

1 code implementation23 Feb 2024 Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua

Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks.

Conversational Web Navigation Instruction Following

Radar-Based Recognition of Static Hand Gestures in American Sign Language

no code implementations20 Feb 2024 Christian Schuessler, Wenxuan Zhang, Johanna Bräunig, Marcel Hoffmann, Michael Stelzig, Martin Vossiek

This emphasizes the practicality of our methodology in overcoming data scarcity challenges and advancing the field of automatic gesture recognition in VR and HCI applications.

Hand Gesture Recognition Hand-Gesture Recognition +1

SeaLLMs -- Large Language Models for Southeast Asia

1 code implementation1 Dec 2023 Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen yang, Chaoqun Liu, Hang Zhang, Lidong Bing

Despite the remarkable achievements of large language models (LLMs) in various tasks, there remains a linguistic bias that favors high-resource languages, such as English, often at the expense of low-resource and regional languages.

Instruction Following

Label Delay in Online Continual Learning

no code implementations1 Dec 2023 Botos Csaba, Wenxuan Zhang, Matthias Müller, Ser-Nam Lim, Mohamed Elhoseiny, Philip Torr, Adel Bibi

We introduce a new continual learning framework with explicit modeling of the label delay between data and label streams over time steps.

Continual Learning

Bridging the Information Gap Between Domain-Specific Model and General LLM for Personalized Recommendation

no code implementations7 Nov 2023 Wenxuan Zhang, Hongzhi Liu, Yingpeng Du, Chen Zhu, Yang song, HengShu Zhu, Zhonghai Wu

Nevertheless, these methods encounter the certain issue that information such as community behavior pattern in RS domain is challenging to express in natural language, which limits the capability of LLMs to surpass state-of-the-art domain-specific models.

Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents

1 code implementation1 Nov 2023 Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs.

Language Modelling Large Language Model

SOUL: Towards Sentiment and Opinion Understanding of Language

1 code implementation27 Oct 2023 Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing

These findings underscore the challenging nature of the SOUL task for existing models, emphasizing the need for further advancements in sentiment analysis to address its complexities.

Language Modelling Sentiment Analysis

Multilingual Jailbreak Challenges in Large Language Models

1 code implementation10 Oct 2023 Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing

The experimental results reveal that in the unintentional scenario, the rate of unsafe content increases as the availability of languages decreases.

JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning

1 code implementation4 Oct 2023 Chang Gao, Wenxuan Zhang, Guizhen Chen, Wai Lam

Instruction tuning has emerged as a crucial process for harnessing the capabilities of large language models (LLMs) by providing explicit task instructions, leading to improved performance in various tasks.

Social Media Fashion Knowledge Extraction as Captioning

no code implementations28 Sep 2023 Yifei Yuan, Wenxuan Zhang, Yang Deng, Wai Lam

Existing work on fashion knowledge extraction in social media is classification-based and requires to manually determine a set of fashion knowledge categories in advance.


ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction

no code implementations1 Sep 2023 Wenxuan Zhang, Xuechao Zou, Li Wu, Xiaoying Wang, Jianqiang Huang, Junliang Xing

Additionally, we construct the RainBench, a large-scale radar echo dataset for precipitation prediction, to address the scarcity of meteorological data in the domain.

Decoder Weather Forecasting

Continual Zero-Shot Learning through Semantically Guided Generative Random Walks

1 code implementation ICCV 2023 Wenxuan Zhang, Paul Janson, Kai Yi, Ivan Skorokhodov, Mohamed Elhoseiny

The GRW loss augments the training by continually encouraging the model to generate realistic and characterized samples to represent the unseen space.

Novel Concepts Zero-Shot Learning

Overcoming Generic Knowledge Loss with Selective Parameter Update

1 code implementation23 Aug 2023 Wenxuan Zhang, Paul Janson, Rahaf Aljundi, Mohamed Elhoseiny

Our method achieves improvements on the accuracy of the newly learned tasks up to 7% while preserving the pretraining knowledge with a negligible decrease of 0. 9% on a representative control set accuracy.

Continual Learning General Knowledge

SLAMB: Accelerated Large Batch Training with Sparse Communication

1 code implementation The International Conference on Machine Learning (ICML) 2023 Hang Xu, Wenxuan Zhang, Jiawei Fei, Yuzhe Wu, Tingwen Xie, Jun Huang, Yuchen Xie, Mohamed Elhoseiny, Panos Kalnis

Distributed training of large deep neural networks requires frequent exchange of massive data between machines, thus communication efficiency is a major concern.

M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

1 code implementation NeurIPS 2023 Wenxuan Zhang, Sharifah Mahani Aljunied, Chang Gao, Yew Ken Chia, Lidong Bing

M3Exam exhibits three unique characteristics: (1) multilingualism, encompassing questions from multiple countries that require strong multilingual proficiency and cultural knowledge; (2) multimodality, accounting for the multimodal nature of many exam questions to test the model's multimodal understanding capability; and (3) multilevel structure, featuring exams from three critical educational periods to comprehensively assess a model's proficiency at different levels.

AQE: Argument Quadruplet Extraction via a Quad-Tagging Augmented Generative Approach

1 code implementation31 May 2023 Jia Guo, Liying Cheng, Wenxuan Zhang, Stanley Kok, Xin Li, Lidong Bing

In this work, we for the first time propose a challenging argument quadruplet extraction task (AQE), which can provide an all-in-one extraction of four argumentative components, i. e., claims, evidence, evidence types, and stances.

Argument Mining Stance Classification +1

Sentiment Analysis in the Era of Large Language Models: A Reality Check

1 code implementation24 May 2023 Wenxuan Zhang, Yue Deng, Bing Liu, Sinno Jialin Pan, Lidong Bing

This paper aims to provide a comprehensive investigation into the capabilities of LLMs in performing various sentiment analysis tasks, from conventional sentiment classification to aspect-based sentiment analysis and multifaceted analysis of subjective texts.

Aspect-Based Sentiment Analysis Few-Shot Learning +2

Zero-Shot Text Classification via Self-Supervised Tuning

1 code implementation19 May 2023 Chaoqun Liu, Wenxuan Zhang, Guizhen Chen, Xiaobao Wu, Anh Tuan Luu, Chip Hong Chang, Lidong Bing

In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning.

Self-Supervised Learning Sentence +5

Enhancing Few-shot NER with Prompt Ordering based Data Augmentation

no code implementations19 May 2023 Huiming Wang, Liying Cheng, Wenxuan Zhang, De Wen Soh, Lidong Bing

Recently, data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER).

Data Augmentation few-shot-ner +4

Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations

1 code implementation17 May 2023 Yang Deng, Wenxuan Zhang, Yifei Yuan, Wai Lam

Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and addressing their problems during the conversation.

Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis

1 code implementation16 May 2023 Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing

Cross-domain aspect-based sentiment analysis (ABSA) aims to perform various fine-grained sentiment analysis tasks on a target domain by transferring knowledge from a source domain.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Easy-to-Hard Learning for Information Extraction

1 code implementation16 May 2023 Chang Gao, Wenxuan Zhang, Wai Lam, Lidong Bing

Information extraction (IE) systems aim to automatically extract structured information, such as named entities, relations between entities, and events, from unstructured texts.

ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions

1 code implementation12 Mar 2023 Deyao Zhu, Jun Chen, Kilichbek Haydarov, Xiaoqian Shen, Wenxuan Zhang, Mohamed Elhoseiny

By keeping acquiring new visual information from BLIP-2's answers, ChatCaptioner is able to generate more enriched image descriptions.

Image Captioning Question Answering +1

Product Question Answering in E-Commerce: A Survey

no code implementations16 Feb 2023 Yang Deng, Wenxuan Zhang, Qian Yu, Wai Lam

Product question answering (PQA), aiming to automatically provide instant responses to customer's questions in E-Commerce platforms, has drawn increasing attention in recent years.

Question Answering

From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader

1 code implementation9 Dec 2022 Weiwen Xu, Xin Li, Wenxuan Zhang, Meng Zhou, Wai Lam, Luo Si, Lidong Bing

We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data.

Classification Extractive Question-Answering +6

SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

1 code implementation CVPR 2023 Wenxuan Zhang, Xiaodong Cun, Xuan Wang, Yong Zhang, Xi Shen, Yu Guo, Ying Shan, Fei Wang

We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.

Image Animation Talking Head Generation

Towards Generalizable and Robust Text-to-SQL Parsing

1 code implementation23 Oct 2022 Chang Gao, Bowen Li, Wenxuan Zhang, Wai Lam, Binhua Li, Fei Huang, Luo Si, Yongbin Li

Text-to-SQL parsing tackles the problem of mapping natural language questions to executable SQL queries.

SQL Parsing Text-To-SQL

A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning

1 code implementation10 Oct 2022 Paul Janson, Wenxuan Zhang, Rahaf Aljundi, Mohamed Elhoseiny

With the success of pretraining techniques in representation learning, a number of continual learning methods based on pretrained models have been proposed.

Continual Learning Representation Learning

UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

1 code implementation ACL 2022 Chang Gao, Wenxuan Zhang, Wai Lam

The goal-oriented document-grounded dialogue aims at responding to the user query based on the dialogue context and supporting document.

Multi-Task Learning Response Generation +1

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

1 code implementation2 Mar 2022 Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, Wai Lam

More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)

User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems

1 code implementation7 Feb 2022 Yang Deng, Wenxuan Zhang, Wai Lam, Hong Cheng, Helen Meng

In this paper, we propose a novel framework, namely USDA, to incorporate the sequential dynamics of dialogue acts for predicting user satisfaction, by jointly learning User Satisfaction Estimation and Dialogue Act Recognition tasks.

Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling

1 code implementation27 Dec 2021 Yang Deng, Yaliang Li, Wenxuan Zhang, Bolin Ding, Wai Lam

Recently, Product Question Answering (PQA) on E-Commerce platforms has attracted increasing attention as it can act as an intelligent online shopping assistant and improve the customer shopping experience.

Answer Generation Question Answering

Domain-Aware Continual Zero-Shot Learning

no code implementations24 Dec 2021 Kai Yi, Paul Janson, Wenxuan Zhang, Mohamed Elhoseiny

Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shifting domains and improved textual representation for unseen classes.

Disentanglement Zero-Shot Learning

Aspect Sentiment Quad Prediction as Paraphrase Generation

1 code implementation EMNLP 2021 Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, Wai Lam

Aspect-based sentiment analysis (ABSA) has been extensively studied in recent years, which typically involves four fundamental sentiment elements, including the aspect category, aspect term, opinion term, and sentiment polarity.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation

no code implementations WNUT (ACL) 2021 Yang Deng, Wenxuan Zhang, Wai Lam

In this work, we propose a novel and easy-to-apply data augmentation strategy, namely Bilateral Generation (BiG), with a contrastive training objective for improving the performance of ranking question answer pairs with existing labeled data.

Answer Generation Data Augmentation +3

Answering Product-related Questions with Heterogeneous Information

no code implementations Asian Chapter of the Association for Computational Linguistics 2020 Wenxuan Zhang, Qian Yu, Wai Lam

Providing instant response for product-related questions in E-commerce question answering platforms can greatly improve users{'} online shopping experience.

Attribute Question Answering

Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond

no code implementations23 Oct 2020 Xin Li, Lidong Bing, Wenxuan Zhang, Zheng Li, Wai Lam

Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks.

Cross-Lingual Transfer Translation

Multi-hop Inference for Question-driven Summarization

1 code implementation EMNLP 2020 Yang Deng, Wenxuan Zhang, Wai Lam

Question-driven summarization has been recently studied as an effective approach to summarizing the source document to produce concise but informative answers for non-factoid questions.

Abstractive Text Summarization

Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce

1 code implementation27 Aug 2020 Yang Deng, Wenxuan Zhang, Wai Lam

There are two main challenges when exploiting the opinion information from the reviews to facilitate the opinion-aware answer generation: (i) jointly modeling opinionated and interrelated information between the question and reviews to capture important information for answer generation, (ii) aggregating diverse opinion information to uncover the common opinion towards the given question.

Answer Generation Opinion Mining +1

Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modeling

no code implementations28 Jun 2020 Wenxuan Zhang, Yang Deng, Wai Lam

In this paper, we investigate the answer ranking problem for product-related questions, with the relevant reviews treated as auxiliary information that can be exploited for facilitating the ranking.

Natural Language Inference Question Answering

Review-guided Helpful Answer Identification in E-commerce

1 code implementation13 Mar 2020 Wenxuan Zhang, Wai Lam, Yang Deng, Jing Ma

In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds' opinions reflected in the reviews, which is another important factor to identify helpful answers.

Answer Selection Community Question Answering

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