Abstract
Semi-supervised learning is a promising way to reduce the annotation cost for text-classification. Combining with pre-trained language models (PLMs), e.g., BERT, recent semi-supervised learning methods achieved impressive performance. In this work, we further investigate the marriage between semi-supervised learning and a pre-trained language model. Unlike existing approaches that utilize PLMs only for model parameter initialization, we explore the inherent topic matching capability inside PLMs for building a more powerful semi-supervised learning approach. Specifically, we propose a joint semi-supervised learning process that can progressively build a standard K-way classifier and a matching network for the input text and the Class Semantic Representation (CSR). The CSR will be initialized from the given labeled sentences and progressively updated through the training process. By means of extensive experiments, we show that our method can not only bring remarkable improvement to baselines, but also overall be more stable, and achieves state-ofthe-art performance in semi-supervised text classification. Code is available at: https://github.com/HeimingX/PCM.
Original language | English |
---|---|
Title of host publication | NAACL 2022, 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference |
Editors | Ryan Cotterell, Danilo Croce, Jordan Zhang |
Place of Publication | Stroudsburg PA USA |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 3003-3013 |
Number of pages | 11 |
ISBN (Electronic) | 9781955917711 |
DOIs | |
Publication status | Published - 2022 |
Externally published | Yes |
Event | North American Association for Computational Linguistics 2022: NAACL 2022 - Seattle, United States of America Duration: 10 Jul 2022 → 15 Jul 2022 https://aclanthology.org/volumes/2022.findings-naacl/ |
Conference
Conference | North American Association for Computational Linguistics 2022 |
---|---|
Abbreviated title | NAACL 2022 |
Country/Territory | United States of America |
City | Seattle |
Period | 10/07/22 → 15/07/22 |
Internet address |