About

I was a Principal Researcher at Microsoft Research (MSR) in the Natural Language Computing group, working with Dr. Furu Wei and Dr. Ming Zhou. My research encompassed a broad range of topics in Natural Language Processing and Machine Learning, with a particular focus on practical technologies for generative language models as well as efficient modeling and inference. I have published over 40 papers at leading Artificial Intelligence conferences such as ACL, NeurIPS, ICLR, EMNLP, and NAACL. I have served as a (senior) area chair and program committee member for these conferences as well as an action editor for top journals like TACL.

Beyond research, I was responsible for the development and deployment of advanced generative models within Microsoft 365 and Office products. I architected and delivered state-of-the-art generative models with highly optimized efficiency that stems from my proposed novel approaches for low-cost GenAI (e.g., Aggressive Decoding, Speculative Decoding and EdgeFormer), enabling the large-scale deployment of these models across various endpoints within our product suite (e.g., Word, Outlook and Edge). The innovative models I developed and rolled out handle billions of user requests daily, amounting to a yearly total that reaches into the trillions, as the most visible and used generative models in Microsoft Editor that transform the writing experience for billions of M365 and Office users with significant product impact.

Prior to joining Microsoft, I earned my Ph.D. from Peking University in 2017, advised by Prof. Zhifang Sui, Baobao Chang and Sujian Li. During my doctoral studies, I also had the privilege of working with Prof. Heng Ji during my visit to Rensselaer Polytechnic Institute (RPI), and with Dr. Jun Suzuki and Dr. Masaaki Nagata during my visit to NTT Communication Science Laboratories.

Publications (#: students I mentored; *: equal contributions; +: Corresponding author)

Preprint

Tech Report

Peer-reviewed

  • Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

    Zhenhailong Wang#, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji

    To appear in NAACL 2024

  • In-context Autoencoder for Context Compression in a Large Language Model

    Tao Ge+, Jing Hu#, Lei Wang#, Xun Wang, Si-Qing Chen, Furu Wei

    To appear in ICLR 2024

  • Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation

    Heming Xia#, Tao Ge*+, Peiyi Wang, Si-Qing Chen, Furu Wei, Zhifang Sui

    In Findings of EMNLP 2023 (Originally announced in March 2022: https://arxiv.org/abs/2203.16487, the first work proposing Speculative Decoding that introduces an independent draft model to accelerate generation explicitly with the idea of speculative execution)

  • Extensible Prompts for Language Models on Zero-shot Language Style Customization

    Tao Ge+, Jing Hu#, Li Dong, Shaoguang Mao, Yan Xia, Xun Wang, Si-Qing Chen, Furu Wei

    In NeurIPS 2023

  • Smart Word Suggestions for Writing Assistance

    Chenshuo Wang, Shaoguang Mao, Tao Ge, Wenshan Wu, Xun Wang, Yan Xia, Jonathan Tien, Dongyan Zhao

    In Findings of ACL 2023

  • Enhancing Detailed Feedback to Chinese Writing Learners Using a Soft-Label Driven Approach and Tag-Aware Ranking Model

    Yuzhe Cai, Shaoguang Mao, Chenshuo Wang, Tao Ge, Wenshan Wu, Yan Xia, Chanjin Zheng, Qiang Guan

    In NLPCC 2023

  • Overview of the NLPCC 2023 Shared Task: Chinese Essay Discourse Coherence Evaluation

    Hongyi Wu, Xinshu Shen, Man Lan, Xiaopeng Bai, Yuanbin Wu, Aimin Zhou, Shaoguang Mao, Tao Ge, Yan Xia

    In NLPCC 2023

  • Overview of CCL23-Eval Task 8: Chinese Essay Fluency Evaluation (CEFE) Task

    Xinshu Shen, Hongyi Wu, Xiaopeng Bai, Yuanbin Wu, Aimin Zhou, Shaoguang Mao, Tao Ge, Yan Xia

    In CCL 2023

  • EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation

    Tao Ge, Si-Qing Chen, Furu Wei

    In EMNLP 2022

  • Plug and Play Knowledge Distillation for kNN-LM with External Logits

    Xuyang Jin#, Tao Ge+, Furu Wei

    In AACL-IJCNLP 2022

  • A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-lingual Language Model

    Xin Sun#, Tao Ge+, Shuming Ma, Jingjing Li, Furu Wei, Houfeng Wang

    In IJCAI 2022

  • Text Revision by On-the-Fly Representation Optimization

    Jingjing Li#, Zichao Li, Tao Ge, Irwin King, Michael Lyu

    In AAAI 2022

  • Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression

    Canwen Xu#, Wangchunshu Zhou#, Tao Ge+, Ke Xu, Julian McAuley, Furu Wei

    In EMNLP 2021

  • Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting

    Wangchunshu Zhou#, Tao Ge+, Canwen Xu#, Ke Xu, Furu Wei

    In EMNLP 2021

  • Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

    Xin Sun*#, Tao Ge*+, Furu Wei, Houfeng Wang

    In ACL 2021

  • Blow the Dog Whistle: A Dataset for Cant Creation, Understanding and Decryption in Chinese

    Canwen Xu*#, Wangchunshu Zhou*#, Tao Ge+, Ke Xu, Julian McAuley, Furu Wei

    In NAACL 2021

  • BERT Loses Patience: Fast and Robust Inference with Early Exit

    Wangchunshu Zhou#, Tao Ge+, Canwen Xu#, Ke Xu, Julian McAuley, Furu Wei

    In NeurIPS 2020

  • UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database

    Canwen Xu#, Tao Ge, Chenliang Li, Furu Wei

    In AACL 2020

  • Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction

    Mengyun Chen#*, Tao Ge*+, Xingxing Zhang, Furu Wei, Ming Zhou

    In EMNLP 2020

  • BERT-of-Theseus: Compressing BERT by Progressive Module Replacing

    Canwen Xu*#, Wangchunshu Zhou*#, Tao Ge+, Ke Xu, Julian McAuley, Furu Wei, Ming Zhou

    In EMNLP 2020

  • Pseudo-Bidirectional Decoding for Local Sequence Transduction

    Wangchunshu Zhou#, Tao Ge, Chang Mu, Ke Xu, Furu Wei, Ming Zhou

    In Findings of EMNLP 2020

  • Improving Grammatical Error Correction with Machine Translation Pairs

    Wangchunshu Zhou#, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

    In Findings of EMNLP 2020

  • Scheduled DropHead: A Regularization Method for Transformer Models

    Wangchunshu Zhou#, Tao Ge, Furu Wei, Ming Zhou, Ke Xu

    In Findings of EMNLP 2020

  • Parallel Data Augmentation for Formality Style Transfer

    Yi Zhang#, Tao Ge, Xu Sun

    In ACL 2020

  • Self-Adversarial Learning with Comparative Discrimination for Text Generation

    Wangchunshu Zhou#, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

    In ICLR 2020

  • Fact-aware Sentence Split and Rephrase with Permutation Invariant Training

    Yinuo Guo#, Tao Ge, Furu Wei

    In AAAI 2020

  • Bert-based Lexical Substitution

    Wangchunshu Zhou#, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

    In ACL 2019

  • Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study

    Tao Ge, Xingxing Zhang, Furu Wei, Ming Zhou

    In ACL 2019

  • Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition

    Tao Ge, Qing Dou, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou

    In EMNLP 2018

  • Fluency Boost Learning and Inference for Neural Grammatical Error Correction

    Tao Ge, Furu Wei, Ming Zhou

    In ACL 2018

  • EventWiki: A Knowledge Base of Major Events

    Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou

    In LREC 2018

  • SeRI: A Dataset for Sub-event Relation Inference from an Encyclopedia

    Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou

    In NLPCC 2018

  • Event detection with Burst Information Networks

    Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou

    In COLING 2016

  • News Stream Summarization using Burst Information Networks

    Tao Ge, Lei Cui, Heng Ji, Baobao Chang, Sujian Li, Ming Zhou, Zhifang Sui

    In EMNLP 2016

  • Discovering Concept-level Event Associations from a Text Stream

    Tao Ge, Lei Cui, Heng Ji, Baobao Chang, Zhifang Sui

    In NLPCC 2016 (Best student paper)

  • Towards Time-aware Knowledge Graph Completion

    Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Baobao Chang, Sujian Li, Zhifang Sui

    In COLING 2016

  • Encoding Temporal Information for Time-aware Link Prediction

    Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui

    In EMNLP 2016

  • One Tense per Scene: Predicting Tense in Chinese Conversations

    Tao Ge, Heng Ji, Baobao Chang, Zhifang Sui

    In ACL 2015

  • Bring you to the past: Automatic Generation of Topically Relevant Event Chronicles

    Tao Ge, Wenzhe Pei, Heng Ji, Sujian Li, Baobao Chang, Zhifang Sui

    In ACL 2015

  • An Effective Neural Network Model for Graph-based Dependency Parsing

    Wenzhe Pei, Tao Ge, Baobao Chang

    In ACL 2015

  • Exploiting task-oriented resources to learn word embeddings for clinical abbreviation expansion

    Yue Liu, Tao Ge, Kusum S Mathews, Heng Ji, Deborah McGuinness

    In BioNLP 2015

  • Max-Margin Tensor Neural Network for Chinese Word Segmentation

    Wenzhe Pei, Tao Ge, Baobao Chang

    In ACL 2014

  • A semi-supervised method for opinion target extraction

    Tao Ge, Wenjie Li, Zhifang Sui

    In WWW 2014

  • The CIPS-SIGHAN CLP 2014 Chinese Word Segmentation Bake-off

    Huiming Duan, Zhifang Sui, Tao Ge

    In CIPS-SIGHAN 2014

  • Exploiting Collaborative Filtering Techniques for Automatic Assessment of Student Free-text Responses

    Tao Ge, Zhifang Sui, Baobao Chang

    In CIKM 2013

  • Event-Based Time Label Propagation for Automatic Dating of News Articles

    Tao Ge, Baobao Chang, Sujian Li, Zhifang Sui

    In EMNLP 2013*