Abstract
We show that MaxEnt is so rich that it can distinguish between any two different mappings: there always exists a nonnegative weight vector which assigns them different MaxEnt probabilities. Stochastic HG instead does admit equiprobable mappings and we give a complete formal characterization of them.- Anthology ID:
- W19-4215
- Volume:
- Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- ACL
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 125–134
- Language:
- URL:
- https://aclanthology.org/W19-4215
- DOI:
- 10.18653/v1/W19-4215
- Cite (ACL):
- Arto Anttila, Scott Borgeson, and Giorgio Magri. 2019. Equiprobable mappings in weighted constraint grammars. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 125–134, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Equiprobable mappings in weighted constraint grammars (Anttila et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W19-4215.pdf