Abstract
There has been little work on modeling the morphological well-formedness (MWF) of derivatives, a problem judged to be complex and difficult in linguistics. We present a graph auto-encoder that learns embeddings capturing information about the compatibility of affixes and stems in derivation. The auto-encoder models MWF in English surprisingly well by combining syntactic and semantic information with associative information from the mental lexicon.- Anthology ID:
- 2020.acl-main.106
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1127–1138
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.106
- DOI:
- 10.18653/v1/2020.acl-main.106
- Cite (ACL):
- Valentin Hofmann, Hinrich Schütze, and Janet Pierrehumbert. 2020. A Graph Auto-encoder Model of Derivational Morphology. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1127–1138, Online. Association for Computational Linguistics.
- Cite (Informal):
- A Graph Auto-encoder Model of Derivational Morphology (Hofmann et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/landing_page/2020.acl-main.106.pdf