Abstract
This paper presents the Instituto de Telecomunicações–Instituto Superior Técnico submission to Task 1 of the SIGMORPHON 2019 Shared Task. Our models combine sparse sequence-to-sequence models with a two-headed attention mechanism that learns separate attention distributions for the lemma and inflectional tags. Among submissions to Task 1, our models rank second and third. Despite the low data setting of the task (only 100 in-language training examples), they learn plausible inflection patterns and often concentrate all probability mass into a small set of hypotheses, making beam search exact.- Anthology ID:
- W19-4207
- Volume:
- Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Garrett Nicolai, Ryan Cotterell
- Venue:
- ACL
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 50–56
- Language:
- URL:
- https://aclanthology.org/W19-4207
- DOI:
- 10.18653/v1/W19-4207
- Cite (ACL):
- Ben Peters and André F. T. Martins. 2019. IT–IST at the SIGMORPHON 2019 Shared Task: Sparse Two-headed Models for Inflection. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 50–56, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- IT–IST at the SIGMORPHON 2019 Shared Task: Sparse Two-headed Models for Inflection (Peters & Martins, ACL 2019)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/W19-4207.pdf