Related papers: Contrastive Bootstrapping for Label Refinement

URL: http://arxiv.org/abs/2306.04544v1
Date: Wed, 7 Jun 2023 15:49:04 GMT
Title: Contrastive Bootstrapping for Label Refinement
Authors: Shudi Hou, Yu Xia, Muhao Chen, Sujian Li
Abstract summary: We propose a lightweight contrastive clustering-based bootstrapping method to iteratively refine the labels of passages. Experiments on NYT and 20News show that our method outperforms the state-of-the-art methods by a large margin.
Score: 34.55195008779178
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Traditional text classification typically categorizes texts into pre-defined coarse-grained classes, from which the produced models cannot handle the real-world scenario where finer categories emerge periodically for accurate services. In this work, we investigate the setting where fine-grained classification is done only using the annotation of coarse-grained categories and the coarse-to-fine mapping. We propose a lightweight contrastive clustering-based bootstrapping method to iteratively refine the labels of passages. During clustering, it pulls away negative passage-prototype pairs under the guidance of the mapping from both global and local perspectives. Experiments on NYT and 20News show that our method outperforms the state-of-the-art methods by a large margin.

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.