Wei Li

wei.li@nus.edu.sg

COM4/05/01

Kent Ridge Campus

Hi, I am Wei Li, a Research Fellow at School of Computing, National University of Singapore, under the supervision of Prof. Yang You. I received my Bachelor of Industrial Engineering from Shanghai Jiao Tong University in 2015. After that, I obtained my M.S. in Management Science and Engineering from University of Chinese Academy of Sciences in 2018. I got my Ph.D Degree from Nanyang Technological University in 2023. I have published several research papers on top-tier conferences and journals including AAAI, ACL, EMNLP Finding, TNNLS and IEEE TAFFC. I also serve as an active reviewer of several journals and conferences, e.g., TNNLS, KBS, INFORM FUSION, NEUCOM, COLING, AAAI, EMNLP, ACL, and EACL.

My diverse educational background (biology, industrial engineering, management science and computer science) gives me the confidence to take on challenging work across different fields. I am also eager to collaborate with people from different domains. My current research interests include: Emotion Recognition in Conversations, Conversational Emotion-cause Pair Extraction, and The Safety Problem of Large Language Models. Besides, I have close collaboration with my teammates in Persona-based Dialogue Generation. Please click publications or GitHub GitHub on the navigation bar for detailed information. During my leisure time, I like playing snooker and swimming.

I am in the job market now! Please feel free to drop me an email or a message to LinkedIn if you are interested. Thank you.

what I did in research during PhD study

I developed a framework for conversational sentiment analysis using generalized neural tensor network as a contextulizer.
I proposed to further improve the performance of conversational sentiment analysis by integrating utterance-level symbolic knowledge and concept-level symbolic knowledge.
I introduced a new task to extract emotion-cause pairs from conversations and built a new dataset accordingly.
I presented the mathematical explanation for NTN from the perspective of Taylor's theorem.

news

Dec 9, 2023	Our paper Task-Aware Self-Supervised Framework for Dialogue Discourse Parsing gets accepted by Findings of the Association for Computational Linguistics: EMNLP 2023!
May 1, 2023	Our paper PAED: Zero-Shot Persona Attribute Extraction in Dialogues gets accepted in ACL 2023!
Feb 11, 2023	Our paper SKIER A Symbolic Knowledge Integrated Model for Conversational Emotion Recognition gets accepted in AAAI 2023!
Oct 21, 2022	A paper gets accpeted in IEEE Transactions on Affective Computing!
Sep 27, 2021	A paper gets accpeted in Knowledge-Based Systems!

selected publications

AAAI

SKIER: A Symbolic Knowledge Integrated Model for Conversational Emotion Recognition

Wei Li, Luyao Zhu, Rui Mao, and 1 more author

Proceedings of the AAAI Conference on Artificial Intelligence, Jun 2023

Bib PDF Code

@article{Li_Zhu_Mao_Cambria_2023,
  title = {SKIER: A Symbolic Knowledge Integrated Model for Conversational Emotion Recognition},
  volume = {37},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26541},
  doi = {10.1609/aaai.v37i11.26541},
  number = {11},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  author = {Li, Wei and Zhu, Luyao and Mao, Rui and Cambria, Erik},
  year = {2023},
  month = jun,
  pages = {13121-13129},
  dimensions = {true},
}

ACL

PAED: Zero-Shot Persona Attribute Extraction in Dialogues

Luyao Zhu, Wei Li, Rui Mao, and 2 more authors

In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023

Bib PDF Code

@inproceedings{zhu-etal-2023-paed,
  title = {{PAED}: Zero-Shot Persona Attribute Extraction in Dialogues},
  author = {Zhu, Luyao and Li, Wei and Mao, Rui and Pandelea, Vlad and Cambria, Erik},
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month = jul,
  year = {2023},
  address = {Toronto, Canada},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2023.acl-long.544},
  pages = {9771--9787},
  dimensions = {true},
}

ASC

User reviews: Sentiment analysis using lexicon integrated two-channel CNN-LSTM family models

Wei Li, Luyao Zhu*, Yong Shi, and 2 more authors

Applied Soft Computing, Jul 2020

Bib HTML PDF

@article{li2020user,
  title = {User reviews: Sentiment analysis using lexicon integrated two-channel CNN-LSTM family models},
  author = {Li, Wei and Zhu*, Luyao and Shi, Yong and Guo, Kun and Cambria, Erik},
  journal = {Applied Soft Computing},
  volume = {94},
  pages = {106435},
  year = {2020},
  publisher = {Elsevier},
  doi = {10.1016/j.asoc.2020.106435},
  dimensions = {true},
}

NEUROM

BiERU: Bidirectional emotional recurrent unit for conversational sentiment analysis

Wei Li, Wei Shao, Shaoxiong Ji, and 1 more author

Neurocomputing, Jul 2022

Bib HTML PDF Code

@article{li2022bieru,
  title = {BiERU: Bidirectional emotional recurrent unit for conversational sentiment analysis},
  author = {Li, Wei and Shao, Wei and Ji, Shaoxiong and Cambria, Erik},
  journal = {Neurocomputing},
  volume = {467},
  pages = {73--82},
  year = {2022},
  publisher = {Elsevier},
  doi = {10.1016/j.neucom.2021.09.057},
  dimensions = {true},
}

TNNLS

SentiVec: Learning Sentiment-Context Vector via Kernel Optimization Function for Sentiment Analysis

Luyao Zhu, Wei Li, Yong Shi, and 1 more author

IEEE Transactions on Neural Networks and Learning Systems, Jul 2021

Bib HTML PDF

@article{9142399,
  author = {Zhu, Luyao and Li, Wei and Shi, Yong and Guo, Kun},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  title = {SentiVec: Learning Sentiment-Context Vector via Kernel Optimization Function for Sentiment Analysis},
  year = {2021},
  volume = {32},
  number = {6},
  pages = {2561-2572},
  doi = {10.1109/TNNLS.2020.3006531},
  dimensions = {true},
}