News
- [Oct 2023] One paper accepted to EMNLP 2023.
- [Aug 2022] One paper accepted to COLING 2022.
- [Sep. 2022] I joined the Institute of Information Engineering, UCAS as a Ph.D. student.
- [Oct. 2021] I joined the PRC, WeChat AI at Tencent, supervised by Fandong Meng.
- [Jun. 2022] I received B.Eng. from SDU. GPA: 3.91/5.0
|
|
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang
EMNLP, 2023   (Main Conference)
pdf
/
code
In this work, we find that such copying-style degeneration is primarily due to the weak likelihood objective, which allows the model to "cheat" the objective by merely duplicating knowledge snippets in a superficial pattern matching manner based on overlap. To overcome this challenge, we propose a Multi-level Adaptive Contrastive Learning (MACL) framework that dynamically samples negative examples and subsequently penalizes degeneration behaviors at both the token-level and sequence-level. Extensive experiments on the WoW dataset demonstrate the effectiveness of our approach across various pre-trained models and decoding strategies.
|
|
TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation
Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie Zhou
COLING, 2022   (Main Conference)
pdf
/
code
For the KGDG task, we find that the topic shift triggers knowledge alteration, and propose a Topic-shift Aware Knowledge sElector(TAKE) to better locate the relevant parts from the dialogue history at an opportune moment. Experimental results on WoW dataset show that compared with strong baselines, TAKE not only selects knowledge more accurately especially on the unseen test set, but also generates more informative responses on both automatic and human evaluation metrics.
|
|