We are Miulab.

Machine Intelligence & Understanding Laboratory
National Taiwan University


What We Do

Our research focus is the intersection between following areas.

Important!! If you are interested in joining MiuLab, please 1) visit R524 to discuss with current students, 2) check our recent publications for details, and 3) include [MS/PhD/RA Candidate] in your email.

Deep Learning

Apply and improve the state-of-the-art deep learning models for diverse tasks.

Conversational AI

Advance dialogue systems for achieving better conversational AI.

Natural Language Processing

Improve and resolve the current language-related tasks.

What We Have Done

    2023

  1. Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model
    Yen-Ting Lin, Yun-Nung Chen
    paper preprint paper:2311.17487
    [paper] [code]
  2. SELF-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations
    Wei-Lin Chen, Yun-Nung Chen
    In The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
    [paper] [code]
  3. CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation
    Chao-Wei Huang, Chen-Yu Hsu, Tsu-Yuan Hsu, Chen-An Li, Yun-Nung Chen
    In The 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2023)
    [paper] [code]
  4. LLM-EVAL: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models
    Yen-Ting Lin, Yun-Nung Chen
    In The 5th Workshop on Natural Language Processing for Conversational AI (NLP4ConvAI 2023)
    [paper] [code]
  5. Zero-Shot Dialogue Relation Extraction by Relating Explainable Triggers and Relation Names
    Ze-Song Xu, Yun-Nung Chen
    In The 5th Workshop on Natural Language Processing for Conversational AI (NLP4ConvAI 2023)
    [paper] [code]
  6. Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning
    Hui-Chi Kuo, Yun-Nung Chen
    In Findings of the Association for Computational Linguistics: ACL 2023 (Findings of ACL 2023)
    [paper] [code]
  7. Visually-Enhanced Phrase Understanding
    Tsu-Yuan Hsu, Chen-An Li, Chao-Wei Huang, Yun-Nung Chen
    In Findings of the Association for Computational Linguistics: ACL 2023 (Findings of ACL 2023)
    [paper] [code]

    8. 2022

  8. Open-Domain Conversational Question Answering with Historical Answers
    Hung-Chieh Fang, Kuo-Han Hung, Chao-Wei Huang, Yun-Nung Chen
    In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022 (Findings of AACL-IJCNLP 2022)
    [paper] [code]
  9. Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding
    Ya-Hsin Chang, Yun-Nung Chen
    In The 23rd Annual Meeting of the International Speech Communication Association (INTERSPEECH 2022)
    [paper] [code]
  10. TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues
    Po-Wei Lin, Shang-Yu Su, Yun-Nung Chen
    In The 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2022)
    [paper] [code]
  11. Controllable User Dialogue Act Augmentation for Dialogue State Tracking
    Chun-Mao Lai, Ming-Hao Hsu, Chao-Wei Huang, Yun-Nung Chen
    In The 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2022)
    [paper] [code]
  12. PLM-ICD: Automatic ICD Coding with Pretrained Language Models
    Chao-Wei Huang, Shang-Chi Tsai, Yun-Nung Chen
    In The 4th Clinical Natural Language Processing Workshop (Clinical NLP 2022)
    [paper] [code]
  13. SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues (acceptance rate: 25.2%)
    Ssu Chiu, Maolin Li, Yen-Ting Lin, Yun-Nung Chen
    In The 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022)
    [paper] [code]

    14. 2021

  14. Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity (oral paper acceptance rate: 8.8%)
    Po-Nien Kung, Sheng-Siang Yin, Yi-Cheng Chen, Tse-Hsuan Yang, Yun-Nung Chen
    In 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)
    [paper] [oral] [slides] [poster] [code]
  15. Relating Neural Text Degeneration to Exposure Bias
    Ting-Rui Chiang and Yun-Nung Chen
    In The Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP 2021)
    [paper] [poster] [code]
  16. Mitigating Biases in Toxic Language Detection through Invariant Rationalization
    Yung-Sung Chuang, Mingye Gao, Hongyin Luo, James Glass, Hung-Yi Lee, Yun-Nung Chen, and Shang-Wen Li
    In The Fifth Workshop on Online Abuse and Harms (WOAH 2021)
    [paper] [oral] [code]
  17. Modeling Diagnostic Label Correlation for Automatic ICD Coding (acceptance rate: 26%)
    Shang-Chi Tsai, Chao-Wei Huang, Yun-Nung Chen
    In 2021 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT 2021)
    [paper] [code]

    18. 2020

  18. TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation (acceptance rate: 20.1%)
    Chun-Hsing Lin, Siang-Ruei Wu, Hung-yi Lee, Yun-Nung Chen
    In 34th Conference on Neural Information Processing Systems (NeurIPS 2020)
    [paper] [code]
  19. What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding (acceptance rate: 22.4%)
    Yu-An Wang, Yun-Nung Chen
    In The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
    [paper] [code]
  20. Lifelong Language Knowledge Distillation (acceptance rate: 22.4%)
    Yung-Sung Chuang, Shang-Yu Su, Yun-Nung Chen
    In The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
    [paper] [code]
  21. Zero-Shot Rationalization by Multi-Task Transfer Learning from Question Answering (acceptance rate: further 15.5%)
    Po-Nien Kung, Tse-Hsuan Yang, Yicheng Chen, Sheng-Siang Yin, Yun-Nung Chen
    In Findings of EMNLP (2020)
    [paper] [code]
  22. Dual Inference for Improving Language Understanding and Generation (acceptance rate: further 15.5%)
    Shang-Yu Su, Yung-Sung Chuang, Yun-Nung Chen
    In Findings of EMNLP (2020)
    [paper] [code]
  23. Towards Unsupervised Language Understanding and Generation by Joint Dual Learning (acceptance rate: 22.7%)
    Shang-Yu Su, Chao-Wei Huang, Yun-Nung Chen
    In The 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020)
    [paper] [code]
  24. Learning Spoken Language Representations with Neural Lattice Language Modeling (short paper acceptance rate: 17.6%)
    Chao-Wei Huang, Yun-Nung Chen
    In The 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020)
    [paper] [code] [slide]
  25. Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding
    Chao-Wei Huang, Yun-Nung Chen
    In The 45th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020)
    [paper] [code] [slide] [video]
  26. RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
    Chao-Wei Huang, Ting-Rui Chiang, Shang-Yu Su, Yun-Nung Chen
    In Computer Speech & Language (2020)
    [doi] [paper]
  27. Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
    Hao-Tong Ye, Kai-Ling Lo, Shang-Yu Su, Yun-Nung Chen
    In Computer Speech & Language (2020)
    [doi] [paper]
  28. Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer
    Ting-Rui Chiang, Chao-Wei Huang, Shang-Yu Su, Yun-Nung Chen
    In Computer Speech & Language (2020)
    [doi] [paper]
  29. An Empirical Study of Content Understanding in Conversational Question Answering (acceptance rate: 20.6%)
    Ting-Rui Chiang, Hao-Tong Ye, Yun-Nung Chen
    In the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020)
    [paper] [paper] [code] [slide] [poster]

    30. 2019

  30. Adapting Pretrained Transformer to Lattices for Spoken Language Understanding
    Chao-Wei Huang, Yun-Nung Chen
    In 2019 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2019)
  31. Dialogue Environments are Different from Games: Investigating Variants of Deep Q-Networks for Dialogue Policy
    Yu-An Wang, Yun-Nung Chen
    In 2019 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2019)
  32. QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization (oral paper acceptance rate: 4.5%)
    Yi-Ting Yeh, Yun-Nung Chen
    The 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019)
    [paper] [code]
  33. What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition (acceptance rate: 20.5%)
    Ting-Yun Chang, Yun-Nung Chen
    In The 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019)
    [paper] [code] [demo]
  34. DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs (acceptance rate: 23.8%) (Best Paper Award at SoCalNLP 2019)
    Yi-Lin Tuan, Yun-Nung Chen, Hung-Yi Lee
    In The 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019)
    [paper] [code]
  35. Tree Transformer: Integrating Tree Structures into Self-Attention (acceptance rate: 23.8%)
    Yau-shian Wang, Hung-Yi Lee, Yun-Nung Chen
    In The 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019)
    [paper]
  36. FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
    Yi-Ting Yeh, Yun-Nung Chen
    In Machine Reading for Question Answering Workshop at EMNLP (MRQA 2019)
  37. Towards Understanding of Medical Randomized Controlled Trails by Conclusion Generation
    Te-Wei Shieh, Yung-Sung Chuang, Shang-Yu Su, Yun-Nung Chen
    In the 10th International Workshop on Health Text Mining and Information Analysis at EMNLP (LOUHI 2019)
  38. Leveraging Hierarchical Category Knowledge for Data-Imbalanced Multi-Label Diagnostic Text Understanding
    Shang-Chi Tsai, Ting-Yun Chang, Yun-Nung Chen
    In the 10th International Workshop on Health Text Mining and Information Analysis at EMNLP (LOUHI 2019)
  39. Dual Supervised Learning for Natual Language Understanding and Generation (short paper acceptance rate: 18.2%)
    Shang-Yu Su, Chao-Wei Huang, Yun-Nung Chen
    In The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)
    [paper] [paper] [bib]
  40. Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems (oral paper acceptance rate: 12.2%)
    Ting-Rui Chiang, Yun-Nung Chen
    In 2019 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT 2019)
    [paper] [paper] [bib]
  41. Learning Context-Sensitive Time-Decay Attention for Role-Based Dialogue Modeling
    Shang-Yu Su, Pei-Chieh Yuan, Yun-Nung Chen
    In The 44th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)
    [paper] [paper]
  42. Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
    Yu-An Wang, Yu-Kai Huang, Tzu-Chuan Lin, Shang-Yu Su, Yun-Nung Chen
    In The 44th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)
    [paper] [paper] [slide] [code] [demo] [oral]
  43. Compound Variational Auto-Encoder
    Shang-Yu Su, Shan-Wei Lin, Yun-Nung Chen
    In The 44th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)
    [paper]
  44. Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain Adaptation
    Chia-Hsuan Lee, Yun-Nung Chen, Hung-Yi Lee
    In The 44th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)
    [paper]

    45. 2018

  45. BCWS: Bilingual Contextual Word Similarity
    Ta-Chung Chi, Ching-Yen Shih, Yun-Nung Chen
    paper preprint paper:1810.08951
    [paper]
  46. xSense: Learning Sense-Separated Sparse Representations and Textual Definitions for Explainable Word Sense Networks
    Ting-Yun Chang, Ta-Chung Chi, Shang-Chi Tsai, Yun-Nung Chen
    paper preprint paper:1809.03348
    [paper]
  47. Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts
    Chih-Wen Goo, Yun-Nung Chen
    In 7th IEEE Workshop on Spoken Language Technology (SLT 2018)
    [paper] [paper] [code]
  48. Investigating Linguistic Pattern Ordering in Hierarchical Natural Language Generation
    Shang-Yu Su, Yun-Nung Chen
    In 7th IEEE Workshop on Spoken Language Technology (SLT 2018)
    [paper] [code]
  49. CLUSE: Cross-Lingual Unsupervised Sense Embeddings (acceptance rate: 24.6%)
    Ta-Chung Chi, Yun-Nung Chen
    In the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)
    [paper] [code]
  50. Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning (acceptance rate: 24.6%)
    Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen
    In the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)
    [paper] [code]
  51. How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues (acceptance rate: 29%) Shang-Yu Su, Pei-Chieh Yuan, Yun-Nung Chen
    In 2018 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT 2018)
    [paper] [acl] [code]
  52. Natural Language Generation by Hierarchical Decoding with Linguistic Patterns (acceptance rate: 29%)
    Shang-Yu Su, Kai-Ling Lo, Yi-Ting Yeh, Yun-Nung Chen
    In 2018 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT 2018)
    [paper] [acl] [code]
  53. Slot-Gated Modeling for Joint Slot Filling and Intent Prediction (acceptance rate: 29%)
    Chih-Wen Goo, Guang Gao, Yun-Kai Hsu, Chih-Li Huo, Tsung-Chieh Chen, Keng-Wei Hsu, Yun-Nung Chen
    In 2018 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT 2018)
    [paper] [acl] [code]

    54. 2017

  54. Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding
    Po-Chun Chen, Ta-Chung Chi, Shang-Yu Su, Yun-Nung Chen
    In 2017 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2017)
    [paper] [poster] [paper] [doi] [code] [bib]
  55. Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning
    Ta-Chung Chi, Po-Chun Chen, Shang-Yu Su, Yun-Nung Chen
    In The 8th International Joint Conference on Natural Language Processing (IJCNLP 2017)
    [paper] [poster] [acl] [paper] [code] [bib]
  56. MUSE: Modularizing Unsupervised Sense Embeddings (acceptance rate: 22%)
    Guang-He Lee, Yun-Nung Chen
    In the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017)
    [paper] [acl] [code] [poster] [bib]
  57. Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification
    Bo Ru Lu, Frank Shyu, Yun-Nung Chen, Hung-Yi Lee, Lin-Shan Lee
    In The 18th Annual Meeting of the International Speech Communication Association (INTERSPEECH 2017)
    [paper] [isca] [doi]

Who We Are

PhD Students

  • Chao-Wei Huang (Intern@Taiwan AI Labs'17-; Intern@Amazon'20-'21; Intern@Meta'22-'23)
  • Yen-Ting Lin (Intern@Amazon'21-'23)
  • Shang-Chi (Mike) Tsai (Intern@Fubon Bank'19; ASUS AICS PhD Fellowship; Intern@Appier)

Master Students

  • Wen-Yu Chang
  • Po-Hen Chen
  • Si-Chia Chen
  • Yi-Cheng Chen (Intern@Microsoft)
  • Jia-Yin Foo
  • Chang-Sheng Kao
  • Tsung-Shang Lin
  • Ze-Song Xu

Co-Advised Members

Alumni

  • Ting-Yun Chang (Intern@Amazon'20; MS'20 → RA@Academia Sinica'21 → PhD@USC)
  • Ya-Hsin Chang (Intern@Trend'21; MS'22 → SWE@Taboola)
  • Ta-Chung (James) Chi (MS'19 → Intern@Amazon'19 → PhD@CMU)
  • Ting-Rui Chiang (Intern@Taiwan AI Labs'18; MS'20 → MS@CMU → PhD@USC)
  • Ssu Chiu (MS'22 → SWE@LINE)
  • Yung-Sung Chuang (BS'21 → PhD@MIT)
  • Yi-Hsuan Deng (Intern@Verizon Media USA'19; MS'21 → SDE@Google)
  • Chih-Wen Goo (MS'18 → SDE@MediaTek)
  • Hsin-Kai Hsu (MS'23)
  • Chieh-Chi Huang (MS'23)
  • Po-Nien Kung (RA'22 → PhD@UCLA)
  • Hui-Chi Kuo (MS'23 → SDE@MediaTek)
  • Po-Wei Lin (MS'23 → MLE@Dcard → MLE@Appier)
  • Guang-He Lee (MS'17 → PhD@MIT CSAIL → Researcher@Citadel)
  • Jian-Jia Su (MS'19 → SDE@Google)
  • Shang-Yu Su (Intern@MSR'18; Intern@Amazon'19-'20; Intern@Google; Google PhD Fellowship; PhD'21 → Research Scientist@Rakuten Institute of Technology)
  • Yu-An (Andy) Wang (Intern@Taiwan AI Labs'19; MS'21 → SDE@Google)
  • Tze-Teng Wong (MS'20)
  • Yi-Ting Yeh (Intern@Taiwan AI Labs'17; Intern@Oath'18; MS'20 → MS@CMU → SDE@Google)
  • Hao-Tong (Allen) Ye (Intern@Taiwan AI Labs'18; Intern@Uber'19; did not graduate → SWE@Shopee)

Contact Us

Get in touch and let's make something great together.

miulab@csie.ntu.edu.tw +886 (02) 3366-4888 # 524

Where To Find Us

National Taiwan University
Taipei, Taiwan
106 TW

Follow Us

Copyright © All rights reserved | MiuLab & Colorlib