EMNLP 2021 / Data Mining

Weakly-Supervised Text Classification Based on Keyword Graph

A weakly supervised text classification paper that uses keyword graphs to propagate limited supervision into useful classification signals.

Research area

Weak supervision, robust learning, topic modeling, continual graph learning, and digital business experiments form the modern method line.

Publication record

Authors
L Zhang, J Ding, Y Xu, Y Liu, S Zhou
Venue
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Year
2021
Area
Data Mining