Shuyang Li, Jin Cao, Mukund Sridhar, Henghui Zhu, Shang-Wen Li, Wael Hamza, and Julian McAuley, Zero-shot Generalization in Dialog State Tracking through Generative Question Answering, in EACL, 2021. [paper] [BibTeX]

Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh, Shang-Wen Li, and Hung-yi Lee, Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation, in SLT, 2021. [paper] [BibTeX]

Shang-Wen Li, Jason Krone, Shuyan Dong, Yi Zhang, and Yaser Al-onaizan, Meta learning to classify intent and slot labels with noisy few shot examples, in SLT, 2021. [paper] [BibTeX]

Cheng-I Lai, Jin Cao, Sravan Bodapati, and Shang-Wen Li, Towards Semi-Supervised Semantics Understanding from Speech, in Self-Supervised Learning for Speech and Audio Processing workshop at NeurIPS, 2020. [paper] [BibTeX]

Cheng-I Lai, Yung-Sung Chuang, Hung-Yi Lee, Shang-Wen Li, and James Glass, Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining, in arXiv preprint arXiv:2010.13826, 2020. [paper] [BibTeX]

Hongyin Luo, Shang-Wen Li, and James Glass, Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks, in Proceedings of the 3rd Clinical Natural Language Processing Workshop at EMNLP, 2020. [paper] [BibTeX]

Jin Cao, Jun Wang, Wael Hamza, Kelly Vanee, and Shang-Wen Li, Style Attuned Pre-training and Parameter Efficient Fine-tuning for Spoken Language Understanding, in INTERSPEECH 2020. [paper] [BibTeX]

Hongyin Luo, Shang-Wen Li, and James Glass, Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption, in INTERSPEECH 2020. [paper] [BibTeX]

Andy T Liu, Shang-Wen Li, and Hung-yi Lee, Tera: Self-supervised learning of transformer encoder representation for speech, in arXiv preprint arXiv:2007.06028, 2020. [paper] [BibTeX]

Maryam Fazel-Zarandi, Shang-Wen Li, Jin Cao, Jared Casale, Peter Henderson, David Whitney, and Alborz Geramifard, Learning robust dialog policies in noisy environments, in Workshop on Conversational AI Today’s Practice Tomorrow’s Potential, NeurIPS, 2017. [paper] [BibTeX]

Shang-Wen Li, Improving learning experience in MOOCs with educational content linking, MIT PhD dissertation. [paper] [BibTeX]

Chengjie Sun, Shang-Wen Li, and Lei Lin, Thread structure prediction for MOOC discussion forum, in ICYCSEE 2016. [paper] [BibTeX]

Xiangrong Zhang, Chen Li, Shang-Wen Li, Victor Zue, Automated segmentation of MOOC lectures towards customized learning, in ICALT 2016. [paper] [BibTeX]

Shang-Wen Li, and Victor Zue, Linking MOOC courseware to accommodate diverse learner backgrounds, in SLaTE 2015. [paper] [BibTeX]

Shang-Wen Li and Victor Zue, Would linked MOOC courseware enhance information search?, in ICALT 2015. [paper] [BibTeX]

Shang-Wen Li and Piotr Mitros, Learnersourced recommendations for remediation, in ICALT 2015. [paper] [BibTeX]

Sheng-syun Shen, Hung-yi Lee, Shang-Wen Li, Victor Zue, and Lin-shan Lee, Structuring lectures in massive open online courses (moocs) for efficient learning by linking similar sections and predicting prerequisites, in INTERSPEECH 2015. [paper] [BibTeX]

Juho Kim, Philip J Guo, Carrie J Cai, Shang-Wen Li, Krzysztof Z Gajos, and Robert C Miller, Data-driven interaction techniques for improving navigation of educational videos, in UIST 2014. [paper] [BibTeX]

Juho Kim, Shang-Wen Li, Carrie J Cai, Krzysztof Z Gajos, and Robert C Miller, Leveraging video interaction data and content analysis to improve video learning, in CHI Workshop on Learning Innovations at Scale, 2014. [paper] [BibTeX]

Yow-bang Wang, Shang-Wen Li, and Lin-shan Lee, An experimental analysis on integrating multi-stream spectro-temporal, cepstral and pitch information for mandarin speech recognition, in IEEE transactions on audio, speech, and language processing 2013. [paper] [BibTeX]

Shang-Wen Li, , Liang-che Sun, and Lin-shan Lee, Improved tonal language speech recognition by integrating spectro-temporal evidence and pitch information with properly chosen tonal acoustic units, in INTERSPEECH 2011. [paper] [BibTeX]

Shang-Wen Li, Liang-che Sun, and Lin-shan Lee, Multi-stream spectro-temporal and cepstral features based on data-driven hierarchical phoneme clusters, in ICASSP 2011. [paper] [BibTeX]

Shang-Wen Li, Liang-che Sun, and Lin-shan Lee, Improved phoneme recognition by integrating evidence from spectro-temporal and cepstral features, in INTERSPEECH 2010. [paper] [BibTeX]