Min-Yen Kan (BS;MS;PhD Columbia Univ.; SACM, SIEEE) is an Associate Professor and Vice Dean of Undergraduate Studies at the National University of Singapore. Min is an active member of the Association of Computational Linguistics (ACL), currently serving as a co-chair for the ACL Ethics Committee (ACL AEC), and previously as the ACL Anthology Director (2008–2018). He is an associate editor for Information Retrieval and the survey editor for the Journal of AI Research (JAIR).
His research interests include digital libraries, natural language processing and information retrieval. He was recognized as a distinguished speaker by the ACM for natural language processing and digital libraries research. Specific projects include work in the areas of scientific discourse analysis, fact verification, full-text literature mining, lexical semantics and large language models. He leads the Web Information Retrieval / Natural Language Processing Group (WING.NUS) http://wing.comp.nus.edu.sg/
Interests
- Artificial Intelligence
- Computational Linguistics
- Information Retrieval
- Digital Libraries
- Large Language Models
- AI 4 Science
- Ethics in NLP
Education
PhD in Computer Science, 2002
Columbia University
MS in Computer Science, 2000
Columbia University
BSc in Computer Science, 1996
Columbia University
Latest
- AI Scientist
- Beyond Memorization: The Challenge of Random Memory Access in Language Models
- Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations
- Self-Adaptive Sampling for Accurate Video Question Answering on Image Text Models
- UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking
- NNOSE: Nearest Neighbor Occupational Skill Extraction
- CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
- CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability
- Doolittle: Benchmarks and Corpora for Academic Writing Formalization
- ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning
- On the Risk of Misinformation Pollution with Large Language Models
- QACheck: A Demonstration System for Question-Guided Multi-Hop Fact-Checking
- SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables
- The ACL OCL Corpus: Advancing Open Science in Computational Linguistics
- Attacking Open-domain Question Answering by Injecting Misinformation
- FollowupQG: Towards information-seeking follow-up question generation
- Investigating Zero- and Few-shot Generalization in Fact Verification
- Adaptive Multi-Modalities Fusion in Sequential Recommendation Systems
- CS6101 2310 - Large Language Models
- Fact-Checking Complex Claims with Program-Guided Reasoning
- Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation
- Songs Across Borders: Singable and Controllable Neural Lyric Translation
- TraVLR: Now You See It, Now You Don′t! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning
- UDAPTER - Efficient Domain Adaptation Using Adapters
- Understanding Ethics in NLP Authoring and Reviewing
- MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences
- Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge
- CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations
- Lightweight Contextual Logical Structure Recovery
- SSNLP '22
- Comparative Snippet Generation
- GL-CLeF: A Global--Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding
- Interpreting the Robustness of Neural NLP Models to Textual Perturbations
- N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking
- So Different Yet So Alike! Constrained Unsupervised Text Style Transfer
- Reliability Testing for Natural Language Processing Systems
- Zero-shot Fact Verification by Claim Generation
- Unsupervised Multi-hop Question Answering by Question Generation
- Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer
- CS6101 2020 - Conversational Recommendation Systems
- Exploring Question-Specific Rewards for Generating Deep Questions
- Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure
- Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework
- Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding
- Re-examining the Role of Schema Linking in Text-to-SQL
- SciWING-- A Software Toolkit for Scientific Document Processing
- Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen
- It′s Morphin′ Time! Combating Linguistic Discrimination with Inflectional Perturbations
- Semantic Graphs for Generating Deep Questions
- Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
- FANG: Leveraging Social Context for Fake News Detection Using Graph Representation
- Sentiment Aware Neural Machine Translation
- Glocal: Incorporating Global Information in Local Convolution for Keyphrase Extraction
- Predicting Helpful Posts in Open-Ended Discussion Forums: A Neural Architecture
- Resource Mention Extraction for MOOC Discussion Forums
- Treatment Side Effect Prediction from Online User-generated Content
- Identifying Emergent Research Trends by Key Authors and Phrases
- Countering Position Bias in Instructor Interventions in MOOC Discussion Forums
- Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures
- The ACL Anthology: Current State and Future Directions
- Modeling Temporal Progression of Emotional Status in Mental Health Forum: A Recurrent Neural Net Approach
- Exploring characteristics of highly cited authors according to citation location and content
- WING-NUS at SemEval-2017 Task 10: Keyphrase Extraction and Classification as Joint Sequence Labeling
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- BiRank: Towards Ranking on Bipartite Graphs
- Health Forum Thread Recommendation Using an Interest Aware Topic Model
- SWIM: a simple word interaction model for implicit discourse relation recognition
- Using discourse signals for robust instructor intervention prediction
- Proceedings of the Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL)
- Context-aware Image Tweet Modelling and Recommendation
- Fast Matrix Factorization for Online Recommendation with Implicit Feedback
- Linking Organizational Social Network Profiles
- Scrutinizing Mobile App Recommendation: Identifying Important App-Related Indicators
- Interactive Second Language Learning from News Websites
- Keywords, phrases, clauses and sentences: topicality, indicativeness and informativeness at scales
- A comprehensive evaluation of scholarly paper recommendation using potential citation papers
- \"Towards higher relevance and serendipity in scholarly paper recommendation\" by Kazunari Sugiyama and Min-Yen Kan with Martin Vesely as coordinator
- #mytweet via Instagram: Exploring User Behaviour across Multiple Social Networks
- Scholarly Document Information Extraction using Extensible Features for Efficient Higher Order Semi-CRFs
- TriRank: Review-aware Explainable Recommendation by Modeling Aspects
- VELDA: relating an image tweet's text and images
- Exploiting Timelines to Enhance Multi-document Summarization
- Comment-based multi-view clustering of web 2.0 items
- New and improved: modeling versions to improve app recommendation
- Predicting the popularity of web 2.0 items based on user comments
- Chinese Informal Word Normalization: an Experimental Study
- Exploiting Discourse Analysis for Article-Wide Temporal Classification
- Identifying research facilitators in an emerging Asian Research Area
- Mining Scientific Terms and their Definitions: A Study of the ACL Anthology
- Automatic keyphrase extraction from scientific articles
- Mining Informal Language from Chinese Microtext: Joint Word Recognition and Segmentation
- Perspectives on crowdsourcing annotations for natural language processing
- Addressing cold-start in app recommendation: latent user models constructed from twitter followers
- Constructing an anonymous dataset from the personal digital photo libraries of mac app store users
- Exploiting potential citation papers in scholarly paper recommendation
- Extracting and matching authors and affiliations in scholarly documents
- Multimodal alignment of scholarly documents and their presentations
- Understanding and classifying image tweets
- Exploiting Category-Specific Information for Multi-Document Summarization
- Improved Temporal Relation Classification using Dependency Parses and Selective Crowdsourced Annotations
- Combining Coherence Models and Machine Translation Evaluation Metrics for Summarization Evaluation
- Integrating User-Generated Content in the ACL Anthology
- Re-tweeting from a linguistic perspective
- Hidden Markov Model for Event Photo Stream Segmentation
- How do people organize their photos in each event and how does it affect storytelling, searching and interpretation tasks?
- Instructor-centric source code plagiarism detection and plagiarism corpus
- PrEV: preservation explorer and vault for web 2.0 user-generated content
- Automatically Evaluating Text Coherence Using Discourse Relations
- Product review summarization from a deeper perspective
- Serendipitous recommendation for scholarly papers considering relations among researchers
- A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages
- Logical Structure Recovery in Scholarly Articles with Rich Document Features
- Enhancing Morphological Alignment for Translating Highly Inflected Languages
- Evaluating N-gram based Evaluation Metrics for Automatic Keyphrase Extraction
- Towards Automated Related Work Summarization
- SemEval-2010 Task 5 : Automatic Keyphrase Extraction from Scientific Articles
- Extracting Formulaic and Free Text Clinical Research Articles Metadata using Conditional Random Fields
- Domain-specific iterative readability computation
- ForeCite: towards a reader-centric scholarly digital library
- Hierarchical Cost-Sensitive Web Resource Acquisition for Record Matching
- Kairos: proactive harvesting of research paper metadata from scientific conference web sites
- Scholarly paper recommendation via user's recent research interests
- Extracting Domain-Specific Words - A Statistical Approach
- A re-examination of lexical association measures
- Proceedings of the 2009 Workshop on Text and Citation Analysis for Scholarly Digital Libraries (NLPIR4DL)
- Re-examining Automatic Keyphrase Extraction Approaches in Scientific Articles
- Recognizing Implicit Discourse Relations in the Penn Discourse Treebank
- Topological Ordering of Function Words in Hierarchical Phrase-based Translation
- FireCite: lightweight real-time reference string extraction from webpages
- Robust argumentative zoning for sensemaking in scholarly documents
- Scholarly digital libraries at scale: introduction to the special issue on very large digital libraries
- ParsCit: an Open-source CRF Reference String Parsing Package
- The ACL Anthology Reference Corpus: A Reference Dataset for Bibliographic Research in Computational Linguistics
- LyricAlly: Automatic Synchronization of Textual Lyrics to Acoustic Music Signals
- Record matching in digital library metadata
- An empirical study of students' perceptions on e-learning systems
- Math information retrieval: user requirements and prototype implementation
- Modeling Context in Scenario Template Creation
- Slide image retrieval: a preliminary study
- Towards a Webpage-Based Bibliographic Manager
- Document concept lattice for text understanding and summarization
- Ordering Phrases with Function Words
- PSNUS: Web People Name Disambiguation by Simple Clustering with Rich Features
- Soft pattern matching models for definitional question answering
- Supervised categorization of JavaScriptTM using program analysis features
- A rich OPAC user interface with AJAX
- Adaptive sorted neighborhood methods for efficient record linkage
- Keyphrase extraction in scientific publications
- PSNUS: web people name disambiguation by simple clustering with rich features
- SlideSeer: a digital library of aligned document and presentation pairs
- Timestamped Graphs: Evolutionary Models of Text for Multi-Document Summarization
- Web based linkage
- Paraphrase Recognition via Dissimilarity Significance Classification
- Extending corpus-based identification of light verb constructions using a supervised learning framework
- Information Retrieval Technology: Third Asia Information Retrieval Symposium, AIRS 2006, Singapore, October 16-18, 2006, Proceedings (Lecture Notes in Computer Science)
- NPIC: hierarchical synthetic image classification using image search and generic features
- Search engine driven author disambiguation
- Video retrieval using high level features: exploiting query matching and confidence-based weighting
- Customization in a unified framework for summarizing medical literature
- Detecting and supporting known item queries in online public access catalogs
- Fast webpage classification using URL features
- Generic soft pattern models for definitional question answering
- Question answering passage retrieval using dependency relations
- A Public Reference Implementation of the RAP Anaphora Resolution Algorithm
- Review of \"Introduction to digital libraries by G. G. Chowdhury and Sudatta Chowdhury\" London: Facet 2003
- Stylistic and lexical co-training for web block classification
- Unsupervised learning of soft patterns for generating definitions from online news
- Web page classification without the web page
- Automatic text summarization as applied to information retrieval: using indicative and informative summaries
- Corpus-trained Text Generation for Summarization
- Using the Annotated Bibliography as a Resource for Indicative Summarization
- Using librarian techniques in automatic text summarization for information retrieval
- Applying Natural Language Generation to Indicative Summarization
- PERSIVAL: personalized summarization over multimedia health-care information
- Role of Verbs in Document Analysis
- Linear Segmentation and Segment Significance