Publications

[P3] Aligning Language Models to Explicitly Handle Ambiguity

• Hyuhng Joon Kim, Youna Kim, Cheonbok Park, Junyeob Kim, Choonghyun Park, Kang Min Yoo, Sang-goo Lee, and Taeuk Kim 

• arXiv preprint (arXiv:2404.11972)

[P2] Hyper-CL: Conditioning Sentence Representations with Hypernetworks

• Young Hyun Yoo, Jii Cha, Changhyeon Kim, and Taeuk Kim 

• arXiv preprint (arXiv:2403.09490)

[P1] Analysis of Multi-Source Language Training in Cross-Lingual Transfer

• Seong Hoon Lim, Taejun Yun, Jinhyeon Kim, Jihun Choi, and Taeuk Kim 

• arXiv preprint (arXiv:2402.13562)

2024

[C17] BlendX: Complex Multi-Intent Detection with Blended Patterns 

• Yejin Yoon, Jungyeon Lee, Kangsan Kim, Chanhee Park, and Taeuk Kim

• The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

2023

[C16] X-SNS: Cross-Lingual Transfer Prediction through Sub-Network Similarity

• Taejun Yun, Jinhyeon Kim, Deokyeong Kang, Seong Hoon Lim, Jihoon Kim, and Taeuk Kim

• Findings of the Association for Computational Linguistics: EMNLP 2023 (Findings of EMNLP 2023)

[C15] Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP

• Hyuhng Joon Kim, Hyunsoo Cho, Sang-Woo Lee, Junyeob Kim, Choonghyun Park, Sang-goo Lee, Kang Min Yoo, and Taeuk Kim

• Findings of the Association for Computational Linguistics: EMNLP 2023 (Findings of EMNLP 2023)

[C14] Prompt-Augmented Linear Probing: Scaling Beyond The Limit of Few-shot In-Context Learners

• Hyunsoo Cho, Hyuhng Joon Kim, Junyeob Kim, Sang-Woo Lee, Sang-goo Lee, Kang Min Yoo, and Taeuk Kim

• The 37th AAAI Conference on Artificial Intelligence (AAAI 2023)

2022

[C13] Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations

• Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim, Hyunsoo Cho, Hwiyeol Jo, Sang-Woo Lee, Sang-goo Lee, and Taeuk Kim

• The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

[C12] Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble

• Hyunsoo Cho, Choonghyun Park, Jaewook Kang, Kang Min Yoo, Taeuk Kim, and Sang-goo Lee

• Findings of the Association for Computational Linguistics: EMNLP 2022 (Findings of EMNLP 2022)

[C11] Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models

• Taeuk Kim

• The 29th International Conference on Computational Linguistics (COLING 2022)

Before 2022

[C10] Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models

• Taeuk Kim, Bowen Li, and Sang-goo Lee

• Findings of the Association for Computational Linguistics: EMNLP 2021 (Findings of EMNLP 2021)

[C9] Self-Guided Contrastive Learning for BERT Sentence Representations

• Taeuk Kim, Kang Min Yoo, and Sang-goo Lee

• The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021)

[C8] Heads-up! Unsupervised Constituency Parsing via Self-Attention Heads

• Bowen Li, Taeuk Kim, Reinald Kim Amplayo, and Frank Keller

• The 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2020)

[C7] Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction

• Taeuk Kim, Jihun Choi, Daniel Edmiston, and Sang-goo Lee

• International Conference on Learning Representations 2020 (ICLR 2020)

[C6] Cell-aware Stacked LSTMs for Modeling Sentences

• Jihun Choi, Taeuk Kim, and Sang-goo Lee

• The 11th Asian Conference on Machine Learning (ACML 2019)

[C5] Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja

• Taeuk Kim*, Kang Min Yoo*, and Sang-goo Lee (*: equal contribution)

• Conference on Empirical Methods in Natural Language Processing 2019 and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019)

[C4] Intrinsic Evaluation of Grammatical Information within Word Embeddings

• Daniel Edmiston and Taeuk Kim

• The 33rd Pacific Asia Conference on Language, Information and Computation (PACLIC 33)

[C3] A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching

• Jihun Choi, Taeuk Kim, and Sang-goo Lee

• The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)

[C2] Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations

• Taeuk Kim, Jihun Choi, Daniel Edmiston, Sanghwan Bae, and Sang-goo Lee

•  Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019)

[C1] Element-wise Bilinear Interaction for Sentence Matching

• Jihun Choi, Taeuk Kim, and Sang-goo Lee

• The Seventh Joint Conference on Lexical and Computational Semantics (*SEM 2018) at NAACL HLT 2018

[W6] Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator

• Hyuhng Joon Kim, Hyunsoo Cho, Junyeob Kim, Taeuk Kim, Kang Min Yoo, and Sang-goo Lee

• Workshop on Large-scale Pre-trained Language Models (LPLM 2022) at NAACL 2022

[W5] HYU at SemEval-2022 Task 2: Effective Idiomaticity Detection with Consideration at Different Levels of Contextualization

• Youngju Joung and Taeuk Kim

• International Workshop on Semantic Evaluation (SemEval 2022) at NAACL 2022

[W4] IDS at SemEval-2020 Task 10: Does Pre-trained Language Model Know What to Emphasize?

• Jaeyoul Shin, Taeuk Kim, and Sang-goo Lee

• International Workshop on Semantic Evaluation (SemEval 2020) at COLING 2020

[W3] Summary Level Training of Sentence Rewriting for Abstractive Summarization

• Sanghwan Bae, Taeuk Kim, Jihoon Kim, and Sang-goo Lee

• The Second Workshop on New Frontiers in Summarization (NewSum 2019) at EMNLP-IJCNLP 2019

[W2] SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension

• Taeuk Kim, Jihun Choi, and Sang-goo Lee

• International Workshop on Semantic Evaluation (SemEval 2018) at NAACL HLT 2018

[W1] A Syllable-based Technique for Word Embeddings of Korean Words

• Sanghyuk Choi, Taeuk Kim, Jinseok Seol, and Sang-goo Lee

• The 1st Workshop on Subword and Character level models in NLP (SCLeM 2017) at EMNLP 2017

[D5] 대조학습 기반 문장표현 방법론 개선을 위한 공통 오류 분석 및 앙상블 기법
(Enhancing Sentence Representations with Common Error Analysis and Ensemble Techniques in Contrastive Learning)

• Jii Cha and Taeuk Kim

• Korea Software Congress 2023 (KSC 2023)

[D4] 효과적인 한국어 교차언어 전송을 위한 특성 연구
(Research on Features for Effective Cross-Lingual Transfer in Korean)

• Taejun Yun and Taeuk Kim

• The 35th Annual Conference on Human and Cognitive Language Technology (HCLT 2023)

[D3] MAdapter: 효율적인 중간 층 도입을 통한 Adapter 구조 개선
(MAdapter: A Refinement of Adapters by Augmenting Efficient Middle Layers)

• Jinhyeon Kim and Taeuk Kim

• The 35th Annual Conference on Human and Cognitive Language Technology (HCLT 2023)

[D2] 원천 언어 다각화를 통한 교차 언어 전이 성능 향상
(Enhanced Zero-Shot Cross-Lingual Transfer with the Diversification of Source Languages)

• Seong Hoon Lim and Taeuk Kim

• Korea Computer Congress 2023 (KCC 2023)

[D1] 한국어 문장 표현을 위한 비지도 대조 학습 방법론의 비교 및 분석
(Comparison and Analysis of Unsupervised Contrastive Learning Approaches for Korean Sentence Representations)

• Young Hyun Yoo, Kyumin Lee, Minjin Jeon, Jii Cha, Kangsan Kim, and Taeuk Kim

• The 34th Annual Conference on Human and Cognitive Language Technology (HCLT 2022)