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
1 code implementation • EMNLP 2021 • Wenxuan Zhang, Ruidan He, Haiyun Peng, Lidong Bing, Wai Lam
Many efforts have been made in solving the Aspect-based sentiment analysis (ABSA) task.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
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.
no code implementations • 30 May 2024 • Ruochen Zhao, Wenxuan Zhang, Yew Ken Chia, Deli Zhao, Lidong Bing
To provide an automatic, robust, and trustworthy evaluation framework, we innovatively propose the Auto-Arena of LLMs, which automates the entire evaluation process with LLM agents.
1 code implementation • 19 Apr 2024 • Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip H. S. Torr, Adel Bibi, Mohamed Elhoseiny
DietCL meticulously allocates computational budget for both types of data.
no code implementations • 15 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.
no code implementations • 29 Feb 2024 • Yiran Zhao, Wenxuan Zhang, Guizhen Chen, Kenji Kawaguchi, Lidong Bing
Based on observed language ratio shifts among layers and the relationships between network structures and certain capabilities, we hypothesize the LLM's multilingual workflow ($\texttt{MWork}$): LLMs initially understand the query, converting multilingual inputs into English for task-solving.
1 code implementation • 29 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.
1 code implementation • 23 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.
no code implementations • 20 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.
1 code implementation • 1 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.
no code implementations • 1 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.
no code implementations • 7 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.
1 code implementation • 1 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.
1 code implementation • 27 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.
1 code implementation • 10 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.
1 code implementation • 4 Oct 2023 • Chang Gao, Wenxuan Zhang, Guizhen Chen, Wai Lam
Instruction tuning has become an essential process for optimizing the performance of large language models (LLMs).
no code implementations • 28 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.
no code implementations • 1 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.
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.
1 code implementation • 23 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.
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.
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.
1 code implementation • 31 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.
1 code implementation • 24 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.
no code implementations • 19 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).
1 code implementation • 19 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.
1 code implementation • 17 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.
1 code implementation • 16 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
1 code implementation • 16 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.
1 code implementation • 12 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.
no code implementations • 16 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.
1 code implementation • 9 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.
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.
1 code implementation • 23 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.
1 code implementation • 17 Oct 2022 • Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua
To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC.
1 code implementation • 10 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.
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.
1 code implementation • 14 Apr 2022 • Yang Deng, Wenxuan Zhang, Weiwen Xu, Wenqiang Lei, Tat-Seng Chua, Wai Lam
In this work, we propose a novel Unified MultI-goal conversational recommeNDer system, namely UniMIND.
1 code implementation • 2 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)
1 code implementation • 7 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.
1 code implementation • 27 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.
no code implementations • 24 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.
1 code implementation • Findings (ACL) 2022 • Zhongli Li, Wenxuan Zhang, Chao Yan, Qingyu Zhou, Chao Li, Hongzhi Liu, Yunbo Cao
Math Word Problem (MWP) solving needs to discover the quantitative relationships over natural language narratives.
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.
Ranked #3 on Aspect-Based Sentiment Analysis (ABSA) on TASD
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • ACL 2021 • Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, Wai Lam
Aspect-based sentiment analysis (ABSA) has received increasing attention recently.
Ranked #4 on Aspect Sentiment Triplet Extraction on ASTE-Data-V2
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
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.
no code implementations • COLING 2020 • Yang Deng, Wenxuan Zhang, Wai Lam
Multi-turn response selection has been extensively studied and applied to many real-world applications in recent years.
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.
no code implementations • 23 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.
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.
1 code implementation • 27 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.
no code implementations • 28 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.
1 code implementation • 13 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.
1 code implementation • WS 2019 • Xin Li, Lidong Bing, Wenxuan Zhang, Wai Lam
In this paper, we investigate the modeling power of contextualized embeddings from pre-trained language models, e. g. BERT, on the E2E-ABSA task.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1