Seung-won Hwang

Professor,
Language and Data Intelligence Lab,
Department of Computer Science and Engineering,
Seoul National University

Email: seungwonh[AT]snu.ac.kr

Education/Experience

Research
Teaching

Advising
Advisees
  • 14 PhD alum: Seungtaek Choi, Kyungjae Lee, Jinyoung Yeo, Hyunsouk Cho, Jinwoo Park, Sanghoon Lee, Taesung Lee, Jongwuk Lee, Jongwon Roh, Gaewon You, Gook-pil Roh, Mu-woong Lee, Jinhan Kim, Sunghwan Kim
  • 21 MS alum: Myeongho Jung, Hoyung Kim, Seoho Song, Haein Park, Junsung Son, Hyountaek Yong, Youngdae Kim, Chul-kyoon Kim, Sukhyun Ahn, Myungha Jang, YoungRok Cha, Sunyou Lee, Eric Lee, Minsuk Cho, Gyeongbok Lee, Sunjae Lim, Sunghyun Park, Haeju Park, YoungSeon Na (+2 pursuing PhD w/ me)

    Selected Publications(full list of 100+@DBLP)

    • Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models, EMNLP 2024
    • Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding, EMNLP 2024
    • QuBE: Question-based Belief Enhancement for Agentic LLM, EMNLP 2024
    • Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code, EMNLP 2024
    • Meta-Prompting Efficient Task-Adaptive Query Generator for Retrieval, Findings of EMNLP 2024
    • Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation, Findings of EMNLP 2024
    • ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval, ACL 2024
    • ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models, ACL 2024
    • DADA: Distribution-Aware Domain Adaptation of PLMs for Information Retrieval, Findings of ACL 2024
    • RaDA: Retrieval-augmented Web Agent Planning with LLMs, Findings of ACL 2024
    • HIL: Hybrid Isotropy Learning for Zero-shot Performance in Dense retrieval, NAACL 2024
    • ScriptMix: Mixing Scripts for Low-resource Language Parsing, NAACL 2024
    • ContrastiveMix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval, NAACL 2024 (short)
    • COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning, Findings of NAACL 2024 (short)
    • Chaining Event Spans for Temporal Relation Understanding, EACL 2024
    • Evidentiality-Aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering, Findings of EACL 2024
    • Learning to Rank Generation with Pairwise Partial Rewards, EMNLP 2023
    • On Sample-Efficient Code Generation, EMNLP 2023 (industry)
    • Relevance-assisted Generation for Robust Zero-shot Retrieval, EMNLP 2023 (industry)
    • Multilingual Lottery Tickets to Pretrain Language Models, Findings of EMNLP 2023
    • Consistency is Key: On Data-Efficient Modality Transfer in Speech Translation, Findings of EMNLP 2023 (short)
    • Intervention-Based Alignment of Code Search with Execution Feedback, Findings of EMNLP 2023
    • CR-COPEC: Causal Rationale of Corporate Performance Changes to learn from Financial Reports, Findings of EMNLP 2023
    • On Complementarity Objectives for Hybrid Retrieval, ACL 2023
    • Retrieval-augmented Video Encoding for Instructional Captioning, Findings of ACL 2023
    • When to Read Documents or QA History: On Unified and Selective Open-domain QA, Findings of ACL 2023
    • Two Examples are Better than One: Context Regularization for Gradient-based Prompt Tuning, Findings of ACL 2023
    • Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization, AAAI 2023
    • PLM-based World Models for Text-based Games, EMNLP 2022
    • Towards Compositional Generalization in Code Search, EMNLP 2022 (short)
    • Pseudo-Relevance for Enhancing Document Representation, EMNLP 2022
    • Normalizing Mutual Information for Robust Adaptive Training for Translation. EMNLP 2022 (short)
    • BotsTalk: Machine-Sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets, EMNLP 2022
    • FAD-X: Fusing Adapters for Cross-lingual Transfer to Low-Resource Languages (short), AACL 2022
    • Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization, COLING 2022
    • Collective Relevance Labeling for Passage Retrieval, NAACL 2022 (short)
    • Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption, NAACL 2022 (short)
    • Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning, NAACL 2022
    • ReACC: A Retrieval-Augmented Code Completion Framework, ACL 2022
    • Debiasing Event Understanding for Visual Commonsense Tasks, Findings of ACL 2022 (short)
    • Plug-and-Play Adaptation for Continuously-updated QA, Findings of ACL 2022
    • C2L: Causally Contrastive Learning for Robust Text Classification, AAAI 2022
    • Dual Task Framework for Improving Persona-grounded Dialogue Dataset, AAAI 2022
    • TrustAL: Trustworthy Active Learning using Knowledge Distillation, AAAI 2022
    • Bridging Code-Text Representation Gap using Explanation, ACML 2021
    • Structure-Augmented Keyphrase Generation, EMNLP 2021
    • Robustifying Multi-hop QA through Pseudo-Evidentiality Training, ACL 2021
    • Web Document Encoding for Structure-Aware Keyphrase Extraction, SIGIR 2021 (short)
    • SCOPA : Soft Code-Switching and Pairwise Alignment for Zero-Shot Cross-lingual Transfer, CIKM 2021 (short)
    • Counterfactual Generative Smoothing for Imbalanced Natural Language Classification, CIKM 2021 (short)
    • Label and Context Augmentation for Response Selection at DSTC8, IEEE Transactions on Audio, Speech, and Language Processing (TASLP), 2021
    • Query Generation for Multimodal Documents, EACL 2021
    • Bootstrapping Information Extraction via Conceptualization, ICDE 2021
    • Retriever-Augmented and Controllable Review Generation, COLING 2020
    • Less is More: Attention Supervision with Counterfactuals for Text Classification, EMNLP 2020
    • Conditional Response Augmentation for Dialogue using Knowledge Distillation, INTERSPEECH 2020
    • Training Data Optimization for Pairwise Learning to Rank, ICTIR 2020
    • Instructional Video Summarization using Attentive Knowledge Grounding, ECML 2020 (demo)
    • BERT Is NOT All You Need for Commonsense Inference, ICASSP 2020
    • Segment-then-Rank: Non-factoid Question Answering on Instructional Videos, AAAI 2020
    • Meta-supervision for Attention Using Counterfactual Estimation, ICDM 2019 (short), Highly Rated ICDM Issue Invitation for DSE 2020
    • Conversion Prediction from Clickstream: Modeling Market Prediction and Customer Predictability, IEEE TKDE 2020 (and WSDM 2017)
    • XINA: Explainable Instance Alignment, IEEE TKDE 2020 (and ICDE 2019)
    • Learning with Limited Data for Multilingual Reading Comprehension, EMNLP 2019
    • NL2pSQL: Generating Pseudo-SQL Queries from Under-specified Natural Language Questions, EMNLP 2019
    • MICRON: Multigranular Interaction for Contextualizing Representation in Non-factoid Question Answering, EMNLP 2019 (short)
    • Text Length Adaptation in Sentiment Classification, ACML 2019
    • Soft Representation Learning for Sparse Transfer, ACL 2019
    • Explanatory and Actionable Debugging for Machine Learning: A TableQA Demonstration, SIGIR 2019 (demo)
    • Categorical Metadata Representation for Customized Text Classification, TACL 2019 (ACL19 talk)
    • Paraphrase Diversification using Counterfactual Debiasing, AAAI 2019
    • AutoSense Model for Word Sense Induction, AAAI 2019
    • QADiver: Interactive Framework for Diagnosing QA Models, AAAI 2019 (demo)
    • List Intersection for Web Search: Algorithms, Cost Models, and Optimization, VLDB 2019
    • Adversarial TableQA: Attention Supervision for Question Answering on Tables, ACML 2018 (Best Student Paper Runner-up)
    • Cold-Start Aware User and Product Attention for Sentiment Classification, ACL 2018
    • Mining Cross-Cultural Differences and Similarities in Social Media, ACL 2018
    • Translations as Additional Contexts for Sentence Classification, IJCAI 2018
    • Entity Commonsense Representation for Neural Abstractive Summarization, NAACL 2018
    • Machine-translated Knowledge Transfer for Commonsense Causal Reasoning, AAAI 2018
    • Entity Suggestion with Conceptual Explanation, IJCAI 2017
    • Efficient Keyword-aware Representative Travel Route Recommendation, IEEE TKDE 2017 (and ICDM 2015)
    • Multimodal KB Harvesting for Emerging Spatial Entities, IEEE TKDE 2017 (and AAAI 2016c)
    • Gradable Adjective Embedding for Commonsense Knowledge, PAKDD 2017
    • KBQA: Learning Question Answering over QA Copora and Knowledge Bases, VLDB 2017
    • Graph-based Wrong IsA Relation Detection in a Large-scale Lexical Taxonomy, AAAI 2017
    • Aspect Sentiment Model for Microreviews, ICDM 2017 (short)
    • Probabilistic Prototype Model for Serendipitious Property Mining, COLING 2016
    • Prediction and Predictability for Search Query Acceleration, ACM Transactions on the Web, 2016
    • Processing and Optimizing Main Memory Spatial-Keyword Queries, VLDB 2016
    • Fine-grained Semantic Conceptualization of FrameNet, AAAI 2016a
    • Verb Pattern: A Probablistic Semantic Representation of Verbs, AAAI 2016b
    • Common Sense Causal Reasoning between Short Texts, KR 2016
    • Cross-lingual Type Inference, DASFAA 2016
    • Event Grounding from Multimodal Social Network Fusion, ICDM 2016 (short)
    • Browsing2purchase: Online Customer Model for Sales Forcasting in an E-commerce Site, WWW 2016 (short)
    • Delayed-Dynamic-Selecive (DDS) Prediction for Reducing Extreme Tail Latencies in Web Search, WSDM 2015 (Best Paper Runner-up)
    • An Association Network for Computing Semantic Relatedness, AAAI 2015
    • Predictive Parallelization: Taming Tail Latencies in Web Search, SIGIR 2014
    • ARIA: Asymmetry Resistant Instance Alignment, AAAI 2014
    • Overcoming Asymmetry in Entity Graphs, IEEE Transactions on Knowledge and Data Engineering 2014
    • Toward Scalable Indexing for Top-k Queries, IEEE Transactions on Knowledge and Data Engineering 2014 (and ICDE 2012)
    • Hybrid Entity Clustering using Crowds and Data, VLDBJ 2014 (and KDD 2009)
    • Map Translation using Geo-tagged Social Media, EACL 2014 (short)
    • Understanding Relational Temporality of Entities, ACL 2014 (short)
    • Towards Efficient Multidimensional Subspace Skyline Computation, VLDBJ 2013 (and VLDB 2011)
    • Bootstrapping Entity Translation on Weakly Comparable Corpora, ACL 2013
    • Enriching Entity Translation Discovery using Selective Temporality, ACL 2013 (short)
    • Attribute Extraction and Scoring: A Probabilistic Approach, ICDE 2013
    • Robust Distributed Indexing for Locality-Skewed WorkloadsCIKM 2012
    • Enriching Document with Examples: A Corpus Mining Approach, ACM Transactions on Information Systems, 2013 (and AAAI 2010)
    • Efficient Entity Translation Mining: A Parallelized Graph Alignment Approach, ACM Transactions on Information Systems, 2012 (and EMNLP 2010)
    • Ursa: Scalable Load and Power Management in Cloud Storage Systems, ACM Transactions on Storage, 2013 (and Middleware 2011)
    • Entity Translation Mining from Comparable Corpora: Combining Graph Mapping with Corpus Latent Features, IEEE Transactions on Knowledge and Data Engineering, 2013 (and CIKM 2011)
    • Predictive Mining of Comparable Entities from the Web, AAAI 2012
    • An Efficient Dual-Resolution Layer Indexing for Top-k Queries, ICDE 2012
    • QSkycube: Efficient Skycube Computation Using Point-Based Space Partitioning, VLDB 2011
    • Web Scale Taxonomy Cleansing, VLDB 2011
    • CosTriage: A Cost-Aware Triage Algorithm for Bug Reporting Systems, AAAI 2011
    • A New Approach for Processing Ranked Subsequence Matching Based on Ranked Union, SIGMOD 2011
    • Exact Indexing for Support Vector Machines, SIGMOD 2011
    • Instant Code Clone Search, ACM SIGSOFT/FSE (Foundations of Software Engineering) 2010
    • Supporting pattern matching queries over trajectories on road networks, IEEE Transactions on Knowledge and Data Engineering, 2011
    • Spatial Skyline Queries: An Efficient Geometric Algorithm SSTD 2009 (Best Paper Award)
    • >Query Result Clustering for Object-level Search ACM SIGKDD 2009
    • Optimizing Top-k Queries for Middleware Access: A Unified Cost-based ApproachACM Transactions on Database Systems, 2007 (and ICDE 2005) >
    • Probe Minimization by Schedule: Supporting Top-k Queries with Expensive PredicatesIEEE Transactions on Knowledge and Data Engineering, 2007 (and SIGMOD 2002)
    • Automatic Categorization of Query Results, ACM SIGMOD 2004
    Honors and Awards
    • Microsoft Research Outstanding Collaborator Award
    • Paper awards: SSTD 2009 (best), WSDM 2015 (best runner-up), ACML 2018 (best student runner-up)
    • Research/teaching excellence: UIUC CS (teaching, 2003), SNU (teaching, 2023), POSTECH (teaching; 2007-2010), Yonsei (presidential distinguished research award)
    • KFAS doctoral study abroad fellow