Abstract
Research has shown that neural models implicitly encode linguistic features, but there has been no research showing how these encodings arise as the models are trained. We present the first study on the learning dynamics of neural language models, using a simple and flexible analysis method called Singular Vector Canonical Correlation Analysis (SVCCA), which enables us to compare learned representations across time and across models, without the need to evaluate directly on annotated data. We probe the evolution of syntactic, semantic, and topic representations, finding, for example, that part-of-speech is learned earlier than topic; that recurrent layers become more similar to those of a tagger during training; and embedding layers less similar. Our results and methods could inform better learning algorithms for NLP models, possibly to incorporate linguistic information more effectively.- Anthology ID:
- N19-1329
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3257–3267
- Language:
- URL:
- https://aclanthology.org/N19-1329
- DOI:
- 10.18653/v1/N19-1329
- Cite (ACL):
- Naomi Saphra and Adam Lopez. 2019. Understanding Learning Dynamics Of Language Models with SVCCA. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3257–3267, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Understanding Learning Dynamics Of Language Models with SVCCA (Saphra & Lopez, NAACL 2019)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/N19-1329.pdf