Abstract
Off-the-shelf models are widely used by computational social science researchers to measure properties of text, such as sentiment. However, without access to source data it is difficult to account for domain shift, which represents a threat to validity. Here, we treat domain adaptation as a modular process that involves separate model producers and model consumers, and show how they can independently cooperate to facilitate more accurate measurements of text. We introduce two lightweight techniques for this scenario, and demonstrate that they reliably increase out-of-domain accuracy on four multi-domain text classification datasets when used with linear and contextual embedding models. We conclude with recommendations for model producers and consumers, and release models and replication code to accompany this paper.- Anthology ID:
- 2022.findings-acl.288
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3633–3655
- Language:
- URL:
- https://aclanthology.org/2022.findings-acl.288
- DOI:
- 10.18653/v1/2022.findings-acl.288
- Cite (ACL):
- Junshen Chen, Dallas Card, and Dan Jurafsky. 2022. Modular Domain Adaptation. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3633–3655, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Modular Domain Adaptation (Chen et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2022.findings-acl.288.pdf
- Code
- jkvc/modular-domain-adaptation
- Data
- IMDb Movie Reviews, SST