Welcome,
my name is 舒蕾. I am a Research Scientist at G
o
o
g
l
e
, specializing in large language models.
Previously, I worked in Amazon AWS AI and Amazon Alexa AI for to-B and to-C conversational AI respectively. In 2020, I completed my Ph.D. in Computer Science at the University of Illinois at Chicago under Prof. Bing Liu's supervision. I worked with my advisor on sentiment analysis and lifelong learning. I also collaborated with Dr. Piero Molino and Dr. Gokhan Tur on Conversational AI, NLU/NLG research. I closely worked with Hu Xu (FAIR) on representation learning (language modeling, word embedding), open-world learning, meta-learning and question answering. Feel free to explore my work and reach out for discussions and collaborations. Let's move AI forward, together!
Selected Papers
2023
- RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
Lei Shu, Liangchen Luo, Jayakumar Hoskere, Yun Zhu, Canoee Liu, Simon Tong, Jindong Chen, Lei Meng
arXiv:2305.15685 [preprint]
2022
- Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang
ACL 2022 [preprint] [bib] [code] - TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning
Yixuan Su, Fangyu Liu, Zaiqiao Meng, Tian Lan, Lei Shu, Ehsan Shareghi, Nigel Collier
NAACL 2022 [preprint] [code] - Zero-Shot Out-of-Distribution Detection Based on the Pretrained Model CLIP
Sepideh Esmaeilpour, Bing Liu, Eric Robertson, Lei Shu
AAAI 2022 [paper] [bib] - Measuring and Reducing Model Update Regression in Structured Prediction for NLP
Deng Cai, Elman Mansimov, Yi-An Lai, Yixuan Su, Lei Shu, Yi Zhang
NeurIPS 2022 [preprint] - Continual Training of Language Models for Few-Shot Learning
Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu, Lei Shu, Bing Liu
EMNLP 2022 [preprint] [code] - Adapting a Language Model While Preserving its General Knowledge
Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu
EMNLP 2022 [preprint] [code] - Zero-Shot Aspect-Based Sentiment Analysis
Lei Shu, Hu Xu, Bing Liu, Jiahua Chen
arXiv:2202.01924 [preprint]
2021
- ODIST: Open World Classification via Distributionally Shifted Instances
Lei Shu, Yassine Benajiba, Saab Mansour, Yi Zhang
EMNLP Findings 2021 [paper] [bib] [video] - CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks
Zixuan Ke, Bing Liu, Hu Xu, Lei Shu
EMNLP 2021 [code] [bib] - Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
Zixuan Ke, Bing Liu, Nainzu Ma, Hu Xu, Lei Shu
NeurIPS 2021 [code]
2020
- Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
Hu Xu, Lei Shu, Philip S Yu, Bing Liu
COLING 2020 [preprint] - Controllable Text Generation with Focused Variation
Lei Shu, Alexandros Papangelis, Yi-Chia Wang, Gokhan Tur, Hu Xu, Zhaleh Feizollahi, Bing Liu, Piero Molino
EMNLP Findings 2020 [preprint] - DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
Hu Xu, Bing Liu, Lei Shu, Philip S Yu
EMNLP Findings 2020 [preprint] - Learning a Sequence of Sentiment Classification Tasks
Zixuan Ke, Bing Liu, Hao Wang and Lei Shu
ECML-PKDD 2020 [preprint][bib][code]
2019
- Modeling Multi-Action Policy for Task-Oriented Dialogues
Lei Shu, Hu Xu, Bing Liu, Piero Molino (Special thanks go to Alexandros Papangelis and Gokhan Tur)
EMNLP 2019 [preprint][bib][code][poster] - Flexibly-Structured Model for Task-Oriented Dialogues
Lei Shu, Piero Molino, Mahdi Namazifar, Hu Xu, Bing Liu, Huaixiu Zheng, Gokhan Tur
SIGDIAL 2019 [preprint][bib][slides][code] - BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
Hu Xu, Bing Liu, Lei Shu, Philip S. Yu
NAACL 2019 [preprint][code][dataset] - Open-world Learning and Application to Product Classification
Hu Xu, Bing Liu, Lei Shu, P. Yu
WWW 2019 [preprint][code] - Controlled CNN-based sequence labeling for aspect extraction
Lei Shu, Hu Xu, Bing Liu
arXiv 2019 [preprint] - A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution
Hu Xu, Bing Liu, Lei Shu, Philip S Yu
arXiv 2019 [preprint]
2018
- Incorporating the Structure of the Belief State in End-to-End Task-Oriented Dialogue Systems
Lei Shu, Piero Molino, Mahdi Namazifar, Bing Liu, Hu Xu, Huaixiu Zheng, Gokhan Tur
NeurIPS 2018 Conversational AI Workshop [paper][bib] - Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
(Yelp Dataset Challenge Round 12 Grand Prize award)
Hu Xu, Bing Liu, Lei Shu, Philip S. Yu
ACL 2018 [paper][bib][in-domain embedding][code][poster] - Lifelong Domain Word Embedding via Meta-Learning
Hu Xu, Bing Liu, Lei Shu, Philip S. Yu
IJCAI 2018 [paper][bib][slides][code] - Dual Attention Network for Product Compatibility and Function Satisfiability Analysis
Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu
AAAI 2018 [paper][bib][slides][dataset] - Unseen Class Discovery in Open-world Classification
Lei Shu, Hu Xu, Bing Liu
arXiv 2018 [preprint][bib]
2017 and before
- DOC: Deep Open Classification of Text Documents
Lei Shu, Hu Xu, Bing Liu
EMNLP 2017 [paper][bib][video][dataset][code] - Lifelong Learning CRF for Supervised Aspect Extraction
Lei Shu, Hu Xu, Bing Liu
ACL 2017 [paper][bib][video] - Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets
Lei Shu, Bing Liu, Hu Xu, Annice Kim
EMNLP 2016 [paper][bib][video]
Professional Services
- Aera/Session Chair for ACL 2023, ACL ARR 2022 2021, IJCAI 2018
- PC member for ACL, EMNLP, NAACL, EACL, AACL, COLING, INLG, SLT, AAAI, NeurIPS, HLDS, WACV
- Invited Reviewer of IEEE Transactions on Affective Computing, IEEE Access, IEEE/ACM Transactions on Audio, Speech, and Language Processing, Progress in Artificial Intelligence
Awards
- Grand Prize Winner of Yelp Dataset Challenge Round 12