Giter VIP home page Giter VIP logo

I am Weihao Zeng, a postgraduate student at the Pattern Recognition and Intelligent System Laboratory(PRIS-NLP), Beijing University of Posts and Telecommunications, advised by Prof. Weiran Xu. I am also a Research Assistant at the Hong Kong University of Science and Technology, supervised by Prof. Junxian He. Previously, I obtained my Bachelor's degree from the Mathematics Department of the same university. My research interests include large language models(LLMs), instruction tuning, and dialogue systems. I have published several papers at top conferences, including ACL, ICLR, SIGIR, EMNLP, and NAACL.

Feel free to email me for any form of academic cooperation !

I am actively seeking PhD Program opportunities for the Fall of 2025 ^_^

๐Ÿ”ฅ News

  • 2024-03: ๐ŸŽ‰๐ŸŽ‰ One paper have been accepted by NAACL 2024!
  • 2024-02: ๐ŸŽ‰๐ŸŽ‰ One paper have been accepted by LREC-COLING 2024!
  • 2024-01: ๐ŸŽ‰๐ŸŽ‰ One paper have been accepted by ICLR 2024!
  • 2023-05: ๐ŸŽ‰๐ŸŽ‰ Two paper have been accepted by ACL 2023!
  • 2022-10: ๐ŸŽ‰๐ŸŽ‰ One paper has been accepted at the SereTOD 2022 Workshop, EMNLP 2022!
  • 2022-09: ๐Ÿ†๐Ÿ† Achieved the 1st rank on SereTOD 2022 track 2, EMNLP 2022!

๐Ÿ“ Publications

  1. FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue

    Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng, Jingang Wang, Yunsen Xian, Weiran Xu

    ACL 2023 Main Conference paper

  2. Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation

    Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu

    ACL 2023 Main Conference paper

  3. What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

    Wei Liu*, Weihao Zeng*, Keqing He, Yong Jiang, Junxian He

    ICLR 2024 paper

  4. DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations

    Weihao Zeng, Dayuan Fu, Keqing He, Yejie Wang, Yukai Xu, Weiran Xu

    NAACL 2024 paper

  5. BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses

    Weihao Zeng, Keqing He, Yejie Wang, Dayuan Fu, Weiran Xu

    LREC-COLING 2024 paper

  6. Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems

    Weihao Zeng, Keqing He, Zechen Wang, Dayuan Fu, Guanting Dong, Ruotong Geng, Pei Wang, Jingang Wang, Chaobo Sun, Wei Wu, Weiran Xu

    SereTOD 2022 WorkShop, EMNLP 2022 paper

  7. ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge Disentanglement

    Lulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Ruotong Geng, Huixing Jiang, Wei Wu, Weiran Xu

    SIGIR 2022 paper

  8. Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization
    Lulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Weiran Xu, Huixing Jiang, Wei Wu, Yanan Wu
    NAACL 2022
    paper

  9. Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization
    Lulu Zhao, Weihao Zeng, Weiran Xu, Jun Guo
    EMNLP 2021
    paper

  10. TODSum: Task-Oriented Dialogue Summarization with State Tracking
    Lulu Zhao, Fujia Zheng, Keqing He, Weihao Zeng, Yuejie Lei, Huixing Jiang, Wei Wu, Weiran Xu, Jun Guo, Fanyu Meng
    Arxiv 2022
    paper

๐ŸŽ– Competitions and Awards

  • National Scholarship in China (2019/2023)
  • 2022-09: ๐Ÿ†๐Ÿ† Achieved the 1st Award on SereTOD Challenge 2022 track 2, EMNLP 2022!
  • 2021-08: ๐Ÿ†๐Ÿ† Achieved the 4th Award on SMP 2021 Conversational AI Challenge!
  • 2021-09: ๐Ÿ†๐Ÿ† Achieved the 8th Place on CCIR 2021 Intelligent NLU Challenge!

Weihao Zeng's Projects

nlpcda icon nlpcda

ไธ€้”ฎไธญๆ–‡ๆ•ฐๆฎๅขžๅผบๅŒ… ๏ผ› NLPๆ•ฐๆฎๅขžๅผบใ€bertๆ•ฐๆฎๅขžๅผบใ€EDA๏ผšpip install nlpcda

p-tuning-v2 icon p-tuning-v2

An optimized prompt tuning strategy comparable to fine-tuning across model scales and tasks.

paddlenlp icon paddlenlp

NLP Core Library and Model Zoo based on PaddlePaddle 2.0

presumm icon presumm

code for EMNLP 2019 paper Text Summarization with Pretrained Encoders

prompt-tuning icon prompt-tuning

Implementation of "The Power of Scale for Parameter-Efficient Prompt Tuning"

pspincalc icon pspincalc

Package for converting between attitude representations: DCM, Euler angles, Quaternions, and Euler vectors

pytorch-fcn icon pytorch-fcn

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

slot_filling_and_intent_detection_of_slu icon slot_filling_and_intent_detection_of_slu

slot filling, intent detection, joint training, ATIS & SNIPS datasets, the Facebookโ€™s multilingual dataset, MIT corpus, E-commerce Shopping Assistant (ECSA) dataset, CoNLL2003 NER, ELMo, BERT, XLNet

tianchi-2021-xiaobu icon tianchi-2021-xiaobu

2021ๅนดๅ…จ็ƒไบบๅทฅๆ™บ่ƒฝๆŠ€ๆœฏๅˆ›ๆ–ฐๅคง่ต›-่ต›้“ไธ‰-ๅ†™็š„ไปฃ็ ๆฐธ่ฟœ้˜Ÿ

trl icon trl

Train transformer language models with reinforcement learning.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.