Publications

OAG-BERT: Towards a Unified Backbone Language Model for Academic Knowledge Services

Published in The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022

This paper is about training large language model on top of scientific data.

Recommended citation: Liu, Xiao & Yin, Da & Zheng, Jingnan & Zhang, Xingjian & Zhang, Peng & Yang, Hongxia & Yuxiao, Dong & Tang, Jie. (2022). OAG-BERT: Towards a Unified Backbone Language Model for Academic Knowledge Services. 3418-3428. 10.1145/3534678.3539210. http://keg.cs.tsinghua.edu.cn/jietang/publications/KDD22-Liu-et-al-OAG-BERT.pdf

Controllable Generation from Pre-trained Language Models via Inverse Prompting

Published in The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

This paper is about using heuristic methods to improve the quality of generated texts via large language models.

Recommended citation: Zou, Xu & Yin, Da & Zhong, Qingyang & Yang, Hongxia & Yang, Zhilin & Tang, Jie. (2021). Controllable Generation from Pre-trained Language Models via Inverse Prompting. 2450-2460. 10.1145/3447548.3467418. http://keg.cs.tsinghua.edu.cn/jietang/publications/KDD21-Zou-et-al-Controllable-Generation-from-Pre-trained-Language-Models-via-Inverse-Prompting.pdf

MRT: Tracing the Evolution of Scientific Publications

Published in IEEE Transactions on Knowledge and Data Engineering, 2021

This paper is about mining scientific data with machine learning methods.

Recommended citation: Yin, Da & Tam, Weng & Ding, Ming & Tang, Jie. (2021). MRT: Tracing the Evolution of Scientific Publications. IEEE Transactions on Knowledge and Data Engineering. PP. 1-1. 10.1109/TKDE.2021.3088139. http://keg.cs.tsinghua.edu.cn/jietang/publications/TKDE21-Yin-et-al-MRT-Tracing-the-Evolution-of-Scientific-Publications.pdf