no code implementations • EMNLP 2020 • Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, Tat-Seng Chua
By providing a schema linking corpus based on the Spider text-to-SQL dataset, we systematically study the role of schema linking.
no code implementations • sdp (COLING) 2022 • Po-Wei Huang, Abhinav Ramesh Kashyap, Yanxia Qin, Yajing Yang, Min-Yen Kan
Logical structure recovery in scientific articles associates text with a semantic section of the article.
1 code implementation • ACL 2022 • Libo Qin, Qiguang Chen, Tianbao Xie, Qixin Li, Jian-Guang Lou, Wanxiang Che, Min-Yen Kan
Specifically, we employ contrastive learning, leveraging bilingual dictionaries to construct multilingual views of the same utterance, then encourage their representations to be more similar than negative example pairs, which achieves to explicitly align representations of similar sentences across languages.
no code implementations • EMNLP (sdp) 2020 • Abhinav Ramesh Kashyap, Min-Yen Kan
We introduce SciWING, an open-source soft-ware toolkit which provides access to state-of-the-art pre-trained models for scientific document processing (SDP) tasks, such as citation string parsing, logical structure recovery and citation intent classification.
no code implementations • EACL (AdaptNLP) 2021 • Abhinav Ramesh Kashyap, Laiba Mehnaz, Bhavitvya Malik, Abdul Waheed, Devamanyu Hazarika, Min-Yen Kan, Rajiv Ratn Shah
The robustness of pretrained language models(PLMs) is generally measured using performance drops on two or more domains.
1 code implementation • SIGDIAL (ACL) 2021 • Ibrahim Taha Aksu, Zhengyuan Liu, Min-Yen Kan, Nancy Chen
We introduce a synthetic dialogue generation framework, Velocidapter, which addresses the corpus availability problem for dialogue comprehension.
no code implementations • 3 May 2024 • Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li
This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks.
no code implementations • 1 May 2024 • Yuxi Xie, Anirudh Goyal, Wenyue Zheng, Min-Yen Kan, Timothy P. Lillicrap, Kenji Kawaguchi, Michael Shieh
We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process inspired by the successful strategy employed by AlphaZero.
1 code implementation • 20 Apr 2024 • Zekai Li, Yanxia Qin, Qian Liu, Min-Yen Kan
We propose Iterative Facuality Refining on Informative Scientific Question-Answering (ISQA) feedback\footnote{Code is available at \url{https://github. com/lizekai-richard/isqa}}, a method following human learning theories that employs model-generated feedback consisting of both positive and negative information.
2 code implementations • 13 Mar 2024 • Qijiong Liu, Hengchang Hu, Jiahao Wu, Jieming Zhu, Min-Yen Kan, Xiao-Ming Wu
Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios.
1 code implementation • 12 Mar 2024 • Tongyao Zhu, Qian Liu, Liang Pang, Zhengbao Jiang, Min-Yen Kan, Min Lin
Through carefully-designed synthetic tasks, covering the scenarios of full recitation, selective recitation and grounded question answering, we reveal that LMs manage to sequentially access their memory while encountering challenges in randomly accessing memorized content.
1 code implementation • 30 Jan 2024 • Mike Zhang, Rob van der Goot, Min-Yen Kan, Barbara Plank
The labor market is changing rapidly, prompting increased interest in the automatic extraction of occupational skills from text.
no code implementations • 14 Jan 2024 • Hengchang Hu, Qijiong Liu, Chuang Li, Min-Yen Kan
Specifically, we introduce a novel method that enhances the learning of embeddings in SR through the supervision of modality correlations.
no code implementations • 14 Nov 2023 • Xuan Long Do, Kenji Kawaguchi, Min-Yen Kan, Nancy F. Chen
Aligning language models (LMs) with human opinion is challenging yet vital to enhance their grasp of human values, preferences, and beliefs.
1 code implementation • 24 Oct 2023 • Minzhi Li, Taiwei Shi, Caleb Ziems, Min-Yen Kan, Nancy F. Chen, Zhengyuan Liu, Diyi Yang
Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance.
1 code implementation • 16 Oct 2023 • Chuang Li, Yan Zhang, Min-Yen Kan, Haizhou Li
Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain.
1 code implementation • 11 Oct 2023 • Liangming Pan, Xinyuan Lu, Min-Yen Kan, Preslav Nakov
Fact-checking real-world claims often requires complex, multi-step reasoning due to the absence of direct evidence to support or refute them.
1 code implementation • 27 Sep 2023 • Hengchang Hu, Yiming Cao, Zhankui He, Samson Tan, Min-Yen Kan
We leverage the Adaptive Adversarial perturbation based on the widely-applied Factorization Machine (AAFM) as our backbone model.
1 code implementation • 18 Sep 2023 • Liangming Pan, Yunxiang Zhang, Min-Yen Kan
In this paper, we explore zero- and few-shot generalization for fact verification (FV), which aims to generalize the FV model trained on well-resourced domains (e. g., Wikipedia) to low-resourced domains that lack human annotations.
1 code implementation • 14 Sep 2023 • Chuang Li, Hengchang Hu, Yan Zhang, Min-Yen Kan, Haizhou Li
However, not all CRS approaches use human conversations as their source of interaction data; the majority of prior CRS work simulates interactions by exchanging entity-level information.
1 code implementation • 10 Sep 2023 • Yan Meng, Liangming Pan, Yixin Cao, Min-Yen Kan
We introduce the task of real-world information-seeking follow-up question generation (FQG), which aims to generate follow-up questions seeking a more in-depth understanding of an initial question and answer.
1 code implementation • 30 Aug 2023 • Hengchang Hu, Wei Guo, Yong liu, Min-Yen Kan
We propose a graph-based approach (named MMSR) to fuse modality features in an adaptive order, enabling each modality to prioritize either its inherent sequential nature or its interplay with other modalities.
no code implementations • 7 Aug 2023 • Xiachong Feng, Xiaocheng Feng, Xiyuan Du, Min-Yen Kan, Bing Qin
However, existing work has focused on training models on centralized data, neglecting real-world scenarios where meeting data are infeasible to collect centrally, due to their sensitive nature.
2 code implementations • 9 Jul 2023 • Wei Han, Hui Chen, Min-Yen Kan, Soujanya Poria
Video question-answering is a fundamental task in the field of video understanding.
Ranked #10 on TGIF-Frame on TGIF-QA
1 code implementation • 7 Jun 2023 • Taha Aksu, Min-Yen Kan, Nancy F. Chen
A challenge in the Dialogue State Tracking (DST) field is adapting models to new domains without using any supervised data, zero-shot domain adaptation.
1 code implementation • 26 May 2023 • Longshen Ou, Xichu Ma, Min-Yen Kan, Ye Wang
The development of general-domain neural machine translation (NMT) methods has advanced significantly in recent years, but the lack of naturalness and musical constraints in the outputs makes them unable to produce singable lyric translations.
1 code implementation • 24 May 2023 • Yuxi Xie, Guanzhen Li, Min-Yen Kan
We introduce ECHo (Event Causality Inference via Human-Centric Reasoning), a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios.
no code implementations • 24 May 2023 • Shaurya Rohatgi, Yanxia Qin, Benjamin Aw, Niranjana Unnithan, Min-Yen Kan
We present ACL OCL, a scholarly corpus derived from the ACL Anthology to assist Open scientific research in the Computational Linguistics domain.
1 code implementation • 23 May 2023 • Yikang Pan, Liangming Pan, Wenhu Chen, Preslav Nakov, Min-Yen Kan, William Yang Wang
In this paper, we comprehensively investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation and its subsequent impact on information-intensive applications, particularly Open-Domain Question Answering (ODQA) systems.
1 code implementation • 22 May 2023 • Xinyuan Lu, Liangming Pan, Qian Liu, Preslav Nakov, Min-Yen Kan
Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence.
1 code implementation • 22 May 2023 • Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov
Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning.
no code implementations • NeurIPS 2023 • Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, Xu Zhao, Min-Yen Kan, Junxian He, Qizhe Xie
Stochastic beam search balances exploitation and exploration of the search space with temperature-controlled randomness.
no code implementations • 9 Mar 2023 • Xinyuan Lu, Min-Yen Kan
Experiments on our two newly contributed personality datasets -- Amazon-beauty and Amazon-music -- validate our hypothesis, showing performance boosts of 3--28%. Our analysis uncovers that varying personality types contribute differently to recommendation performance: open and extroverted personalities are most helpful in music recommendation, while a conscientious personality is most helpful in beauty product recommendation.
1 code implementation • 7 Feb 2023 • Bhavitvya Malik, Abhinav Ramesh Kashyap, Min-Yen Kan, Soujanya Poria
We even outperform unsupervised domain adaptation methods such as DANN and DSN in sentiment classification, and we are within 0. 85% F1 for natural language inference task, by fine-tuning only a fraction of the full model parameters.
1 code implementation • 3 Jan 2023 • Longxu Dou, Yan Gao, Xuqi Liu, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Min-Yen Kan, Jian-Guang Lou
In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables.
1 code implementation • 23 Oct 2022 • Wei Han, Hui Chen, Min-Yen Kan, Soujanya Poria
Existing multimodal tasks mostly target at the complete input modality setting, i. e., each modality is either complete or completely missing in both training and test sets.
no code implementations • COLING 2022 • Lin Xu, Qixian Zhou, Jinlan Fu, Min-Yen Kan, See-Kiong Ng
Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally.
1 code implementation • 23 Sep 2022 • Hengchang Hu, Liangming Pan, Yiding Ran, Min-Yen Kan
Prerequisites can play a crucial role in users' decision-making yet recommendation systems have not fully utilized such contextual background knowledge.
1 code implementation • ECNLP (ACL) 2022 • Saurabh Jain, Yisong Miao, Min-Yen Kan
We model product reviews to generate comparative responses consisting of positive and negative experiences regarding the product.
1 code implementation • ACL 2022 • Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann, Soujanya Poria
Automatic transfer of text between domains has become popular in recent times.
1 code implementation • 18 Apr 2022 • Libo Qin, Qiguang Chen, Tianbao Xie, Qixin Li, Jian-Guang Lou, Wanxiang Che, Min-Yen Kan
We present Global--Local Contrastive Learning Framework (GL-CLeF) to address this shortcoming.
1 code implementation • 21 Nov 2021 • Keng Ji Chow, Samson Tan, Min-Yen Kan
Furthermore, existing V+L benchmarks often report global accuracy scores on the entire dataset, making it difficult to pinpoint the specific reasoning tasks that models fail and succeed at.
1 code implementation • 15 Oct 2021 • Liangming Pan, Wenhu Chen, Min-Yen Kan, William Yang Wang
We curate both human-written and model-generated false documents that we inject into the evidence corpus of QA models and assess the impact on the performance of these systems.
no code implementations • Findings (ACL) 2022 • Yunxiang Zhang, Liangming Pan, Samson Tan, Min-Yen Kan
In this work, we test the hypothesis that the extent to which a model is affected by an unseen textual perturbation (robustness) can be explained by the learnability of the perturbation (defined as how well the model learns to identify the perturbation with a small amount of evidence).
1 code implementation • ACL 2021 • Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang
However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive.
no code implementations • ACL 2021 • Samson Tan, Shafiq Joty, Kathy Baxter, Araz Taeihagh, Gregory A. Bennett, Min-Yen Kan
Questions of fairness, robustness, and transparency are paramount to address before deploying NLP systems.
no code implementations • 26 Apr 2021 • Jiaqi Li, Ming Liu, Zihao Zheng, Heng Zhang, Bing Qin, Min-Yen Kan, Ting Liu
Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC.
Ranked #4 on Question Answering on Molweni
no code implementations • Findings (ACL) 2022 • Taha Aksu, Zhengyuan Liu, Min-Yen Kan, Nancy F. Chen
Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure.
1 code implementation • COLING 2020 • Akshay Bhola, Kishaloy Halder, Animesh Prasad, Min-Yen Kan
We introduce a deep learning model to learn the set of enumerated job skills associated with a job description.
1 code implementation • COLING 2020 • Yuxi Xie, Liangming Pan, Dongzhe Wang, Min-Yen Kan, Yansong Feng
Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing.
no code implementations • NAACL 2021 • Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann
Domain divergence plays a significant role in estimating the performance of a model in new domains.
1 code implementation • NAACL 2021 • Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang
Obtaining training data for multi-hop question answering (QA) is time-consuming and resource-intensive.
no code implementations • 20 Aug 2020 • Liangming Pan, Jingjing Chen, Jianlong Wu, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Yu-Gang Jiang, Tat-Seng Chua
Understanding food recipe requires anticipating the implicit causal effects of cooking actions, such that the recipe can be converted into a graph describing the temporal workflow of the recipe.
1 code implementation • 18 Aug 2020 • Van-Hoang Nguyen, Kazunari Sugiyama, Preslav Nakov, Min-Yen Kan
In particular, FANG yields significant improvements for the task of fake news detection, and it is robust in the case of limited training data.
no code implementations • 15 May 2020 • Ya-Hui An, Muthu Kumar Chandresekaran, Min-Yen Kan, Yan Fu
We demonstrate the feasibility of this approach to the automatic identification, linking and resolution -- a task known as Wikification -- of learning resources mentioned on MOOC discussion forums, from a harvested collection of 100K+ resources.
1 code implementation • ACL 2020 • Samson Tan, Shafiq Joty, Min-Yen Kan, Richard Socher
Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e. g., African American Vernacular English, Colloquial Singapore English, etc.).
no code implementations • ACL 2020 • Yixin Cao, Ruihao Shui, Liangming Pan, Min-Yen Kan, Zhiyuan Liu, Tat-Seng Chua
The curse of knowledge can impede communication between experts and laymen.
1 code implementation • EMNLP 2020 • Samson Tan, Shafiq Joty, Lav R. Varshney, Min-Yen Kan
Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English.
1 code implementation • ACL 2020 • Liangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua, Min-Yen Kan
This paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information of the input passage.
1 code implementation • COLING 2020 • Jiaqi Li, Ming Liu, Min-Yen Kan, Zihao Zheng, Zekun Wang, Wenqiang Lei, Ting Liu, Bing Qin
Research into the area of multiparty dialog has grown considerably over recent years.
Ranked #7 on Discourse Parsing on Molweni
1 code implementation • 8 Apr 2020 • Abhinav Ramesh Kashyap, Min-Yen Kan
We introduce SciWING, an open-source software toolkit which provides access to pre-trained models for scientific document processing tasks, inclusive of citation string parsing and logical structure recovery.
no code implementations • 21 Feb 2020 • Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, Tat-Seng Chua
Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models.
no code implementations • 19 Nov 2019 • Minh-Thang Luong, Preslav Nakov, Min-Yen Kan
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process.
no code implementations • WS 2019 • Chenglei Si, Kui Wu, Ai Ti Aw, Min-Yen Kan
We conducted tests with both sentiment and non-sentiment bearing contexts to examine the effectiveness of our methods.
no code implementations • 28 Oct 2019 • Chenglei Si, Shuohang Wang, Min-Yen Kan, Jing Jiang
Based on our experiments on the 5 key MCRC datasets - RACE, MCTest, MCScript, MCScript2. 0, DREAM - we observe that 1) fine-tuned BERT mainly learns how keywords lead to correct prediction, instead of learning semantic understanding and reasoning; and 2) BERT does not need correct syntactic information to solve the task; 3) there exists artifacts in these datasets such that they can be solved even without the full context.
1 code implementation • 2 Sep 2019 • Kokil Jaidka, Michihiro Yasunaga, Muthu Kumar Chandrasekaran, Dragomir Radev, Min-Yen Kan
This overview describes the official results of the CL-SciSumm Shared Task 2018 -- the first medium-scale shared task on scientific document summarization in the computational linguistics (CL) domain.
1 code implementation • 23 Jul 2019 • Muthu Kumar Chandrasekaran, Michihiro Yasunaga, Dragomir Radev, Dayne Freitag, Min-Yen Kan
All papers are from the open access research papers in the CL domain.
no code implementations • NAACL 2019 • Animesh Prasad, Min-Yen Kan
Graph Convolutional Networks (GCNs) are a class of spectral clustering techniques that leverage localized convolution filters to perform supervised classification directly on graphical structures.
no code implementations • NAACL 2019 • Kishaloy Halder, Min-Yen Kan, Kazunari Sugiyama
Users participate in online discussion forums to learn from others and share their knowledge with the community.
no code implementations • WS 2019 • Animesh Prasad, Chenglei Si, Min-Yen Kan
Datasets are integral artifacts of empirical scientific research.
1 code implementation • 26 May 2019 • Muthu Kumar Chandrasekaran, Min-Yen Kan
We propose novel attention based models to infer the amount of latent context necessary to predict instructor intervention.
no code implementations • 22 May 2019 • Liangming Pan, Wenqiang Lei, Tat-Seng Chua, Min-Yen Kan
Emerging research in Neural Question Generation (NQG) has started to integrate a larger variety of inputs, and generating questions requiring higher levels of cognition.
no code implementations • 21 Nov 2018 • Ya-Hui An, Liangming Pan, Min-Yen Kan, Qiang Dong, Yan Fu
We propose the novel problem of learning resource mention identification in MOOC forums.
2 code implementations • 18 Nov 2018 • Xuan Su, Animesh Prasad, Min-Yen Kan, Kazunari Sugiyama
Citation function and provenance are two cornerstone tasks in citation analysis.
no code implementations • WS 2018 • Van Hoang Nguyen, Kazunari Sugiyama, Min-Yen Kan, Kishaloy Halder
With Health 2. 0, patients and caregivers increasingly seek information regarding possible drug side effects during their medical treatments in online health communities.
1 code implementation • COLING 2018 • Shenhao Jiang, Animesh Prasad, Min-Yen Kan, Kazunari Sugiyama
Identifying emergent research trends is a key issue for both primary researchers as well as secondary research managers.
1 code implementation • ACL 2018 • Wenqiang Lei, Xisen Jin, Min-Yen Kan, Zhaochun Ren, Xiangnan He, Dawei Yin
Existing solutions to task-oriented dialogue systems follow pipeline designs which introduces architectural complexity and fragility.
no code implementations • WS 2017 • Kishaloy Halder, Lahari Poddar, Min-Yen Kan
We study the problem of predicting a patient{'}s emotional status in the future from her past posts and we propose a Recurrent Neural Network (RNN) based architecture to address it.
3 code implementations • 16 Aug 2017 • Xiangnan He, Hanwang Zhang, Min-Yen Kan, Tat-Seng Chua
To address this, we specifically design a new learning algorithm based on the element-wise Alternating Least Squares (eALS) technique, for efficiently optimizing a MF model with variably-weighted missing data.
3 code implementations • 15 Aug 2017 • Xiangnan He, Ming Gao, Min-Yen Kan, Dingxian Wang
In this paper, we study the problem of ranking vertices of a bipartite graph, based on the graph's link structure as well as prior information about vertices (which we term a query vector).
no code implementations • SEMEVAL 2017 • Animesh Prasad, Min-Yen Kan
We describe an end-to-end pipeline processing approach for SemEval 2017{'}s Task 10 to extract keyphrases and their relations from scientific publications.
1 code implementation • 3 Dec 2016 • Muthu Kumar Chandrasekaran, Carrie Demmans Epp, Min-Yen Kan, Diane Litman
We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs).
no code implementations • WS 2016 • Hong Jin Kang, Tao Chen, Muthu Kumar Chandrasekaran, Min-Yen Kan
Thus we have also applied word embeddings to the novel task of cross-lingual WSD for Chinese and provide a public dataset for further benchmarking.
no code implementations • 1 Jan 2015 • Jun-Ping Ng, Min-Yen Kan
In this paper, we motivate the need for a publicly available, generic software framework for question-answering (QA) systems.
1 code implementation • 15 Sep 1998 • Min-Yen Kan, Judith L. Klavans, Kathleen R. McKeown
We present a new method for discovering a segmental discourse structure of a document while categorizing segment function.