Publications

My Semantic Scholar and Google Scholar pages.

*indicates equal contribution

2024

  1. EMNLP Oral
    Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
    Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, and Tagyoung Chung
    In Conference on Empirical Methods in Natural Language Processing (EMNLP) (Oral) (🏆 Best Paper Nomination from a Reviewer), 2024
  2. EMNLP Findings
    LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
    Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, and Nanyun Peng
    In Findings of the Association for Computational Linguistics: EMNLP, 2024
  3. EMNLP WS
    CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints
    Anirudh Atmakuru*, Jatin Nainani*, Rohith Siddhartha Reddy Bheemreddy*, Anirudh Lakkaraju*, Zonghai Yao, Hamed Zamani, and Haw-Shiuan Chang*
    In 6th Workshop on Narrative Understanding (WNU), 2024
  4. NAACL WS
    Fine-to-Coarse Entailment Hierarchy Construction for Coarse-to-Fine Story Generation
    Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, and Tagyoung Chung
    In Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP), 2024
  5. ArXiv
    REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
    Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, and Tagyoung Chung
    arXiv preprint arXiv:2406.07735, 2024
  6. WSDM
    To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders
    Haw-Shiuan Chang, Nikhil Agarwal, and Andrew McCallum
    In Proceedings of The 17th ACM International Conference on Web Search and Data Mining, 2024

2023

  1. ACL Findings
    Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
    Haw-Shiuan Chang*, Zonghai Yao*, Alolika Gon, Hong Yu, and Andrew McCallum
    In Findings of the Association for Computational Linguistics: ACL 2023 (Findings of ACL), 2023
  2. ACL
    Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling
    Haw-Shiuan Chang*, Ruei-Yao Sun*, Kathryn Ricci*, and Andrew McCallum
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2023
  3. ArXiv
    Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens
    Ronald Seoh*, Haw-Shiuan Chang*, and Andrew McCallum
    arXiv preprint arXiv:2309.04333, 2023

2022

  1. Thesis
    Modeling the Multi-mode Distribution in Self-Supervised Language Models
    Haw-Shiuan Chang
    In PhD Thesis, 2022
  2. ACL
    Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions
    Haw-Shiuan Chang, and Andrew McCallum
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2022
  3. SDP
    Unsupervised Partial Sentence Matching for Cited Text Identification
    Kathryn Ricci*, Haw-Shiuan Chang*, Purujit Goyal, and Andrew McCallum
    In Proceedings of the Third Workshop on Scholarly Document Processing, 2022
  4. NAACL WS
    Augmenting Scientific Creativity with Retrieval across Knowledge Domains
    Hyeonsu B. Kang*, Sheshera Mysore*, Kevin Huang*, Haw-Shiuan Chang, Thorben Prein, Andrew McCallum, Aniket Kittur, and Elsa Olivetti
    In Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP), 2022

2021

  1. EACL Oral
    Changing the Mind of Transformers for Topically-Controllable Language Generation
    Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer, and Andrew McCallum
    In Conference of the European Chapter of the Association for Computational Linguistics (EACL) (Oral), 2021
  2. EACL Oral
    Multi-facet Universal Schema
    Rohan Paul*, Haw-Shiuan Chang*, and Andrew McCallum
    In Conference of the European Chapter of the Association for Computational Linguistics (EACL) (Oral), 2021
  3. AAAI
    Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications
    Haw-Shiuan Chang, Amol Agrawal, and Andrew McCallum
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021
  4. EMNLP Short
    Open Aspect Target Sentiment Classification with Natural Language Prompts
    Ronald Seoh*, Ian Birle*, Mrinal Tak*, Haw-Shiuan Chang*, Brian Pinette, and Alfred Hough
    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021

2020

  1. ML
    Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition
    Haw-Shiuan Chang, Shankar Vembu, Sunil Mohan, Rheeya Uppaal, and Andrew McCallum
    Machine Learning, 2020
  2. KDD
    AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
    Xin Luna Dong, Xiang He, Andrey Kan, Xian Li, Yan Liang, Jun Ma, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Gabriel Blanco Saldana, and 12 more authors
    In KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020, 2020
  3. JCIM
    Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks
    Edward Kim, Zach Jensen, Alexander Grootel, Kevin Huang, Matthew Staib, Sheshera Mysore, Haw-Shiuan Chang, Emma Strubell, Andrew McCallum, Stefanie Jegelka, and 1 more author
    J. Chem. Inf. Model., 2020

2019

  1. LAW
    The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures
    Sheshera Mysore, Zach Jensen, Edward Kim, Kevin Huang, Haw-Shiuan Chang, Emma Strubell, Jeffrey Flanigan, Andrew McCallum, and Elsa Olivetti
    In Proceedings of the 13th Linguistic Annotation Workshop at ACL, 2019

2018

  1. TMM
    Active Learning for Crowdsourced QoE Modeling
    Haw-Shiuan Chang, Chih-Fan Hsu, Tobias Hoßfeld, and Kuan-Ta Chen
    IEEE Trans. Multim., 2018
  2. NAACL
    Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
    Haw-Shiuan Chang, ZiYun Wang, Luke Vilnis, and Andrew McCallum
    In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), 2018
  3. TextGraphs
    Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings
    Haw-Shiuan Chang, Amol Agrawal, Ananya Ganesh, Anirudha Desai, Vinayak Mathur, Alfred Hough, and Andrew McCallum
    In TextGraphs-12: the Workshop on Graph-based Methods for Natural Language Processing (NAACL WS), 2018

2017

  1. NeurIPS
    Active Bias: Training a More Accurate Neural Network by Emphasizing High Variance Samples
    Haw-Shiuan Chang, Erik G. Learned-Miller, and Andrew McCallum
    In Advances in Neural Information Processing Systems (NeurIPS), 2017
  2. NeurIPS WS
    Automatically Extracting Action Graphs from Materials Science Synthesis Procedures
    Sheshera Mysore, Edward Kim, Emma Strubell, Ao Liu, Haw-Shiuan Chang, Srikrishna Kompella, Kevin Huang, Andrew McCallum, and Elsa Olivetti
    In Workshop on Machine Learning for Molecules and Materials at NIPS, 2017

2016

  1. TAC/KBP
    Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema
    Haw-Shiuan Chang, Abdurrahman Munir, Ao Liu, Johnny Tian-Zheng Wei, Aaron Traylor, Ajay Nagesh, Nicholas Monath, Patrick Verga, Emma Strubell, and Andrew McCallum
    In Text Analysis Conference, Knowledge Base Population (TAC/KBP), 2016

2015

  1. EDM Short
    Modeling Exercise Relationships in E-Learning: A Unified Approach
    Haw-Shiuan Chang, Hwai-Jung Hsu, and Kuan-Ta Chen
    In International Conference on Educational Data Mining (EDM), 2015
  2. CVIU
    Optimizing the Decomposition for Multiple Foreground Cosegmentation
    Haw-Shiuan Chang, and Yu-Chiang Frank Wang
    Computer Vision and Image Understanding (CVIU), 2015

2014

  1. ACCV
    Simple-to-Complex Discriminative Clustering for Hierarchical Image Segmentation
    Haw-Shiuan Chang, and Yu-Chiang Frank Wang
    In Asian Conference on Computer Vision (ACCV), 2014

2013

  1. ICIP
    Superpixel-based Large Displacement Optical Flow
    Haw-Shiuan Chang, and Yu-Chiang Frank Wang
    In IEEE International Conference on Image Processing, ICIP, 2013
  2. TIP
    Exploring Visual and Motion Saliency for Automatic Video Object Extraction
    Wei-Te Li, Haw-Shiuan Chang, Kuo-Chin Lien, Hui-Tang Chang, and Yu-Chiang Frank Wang
    IEEE Transactions on Image Processing, 2013