NEMO: Frequentist Inference Approach to Constrained Linguistic Typology Feature Prediction in SIGTYP 2020 Shared Task

Alexander Gutkin, Richard Sproat


Abstract
This paper describes the NEMO submission to SIGTYP 2020 shared task (Bjerva et al., 2020) which deals with prediction of linguistic typological features for multiple languages using the data derived from World Atlas of Language Structures (WALS). We employ frequentist inference to represent correlations between typological features and use this representation to train simple multi-class estimators that predict individual features. We describe two submitted ridge regression-based configurations which ranked second and third overall in the constrained task. Our best configuration achieved the microaveraged accuracy score of 0.66 on 149 test languages.
Anthology ID:
2020.sigtyp-1.3
Volume:
Proceedings of the Second Workshop on Computational Research in Linguistic Typology
Month:
November
Year:
2020
Address:
Online
Editors:
Ekaterina Vylomova, Edoardo M. Ponti, Eitan Grossman, Arya D. McCarthy, Yevgeni Berzak, Haim Dubossarsky, Ivan Vulić, Roi Reichart, Anna Korhonen, Ryan Cotterell
Venue:
SIGTYP
SIG:
SIGTYP
Publisher:
Association for Computational Linguistics
Note:
Pages:
17–28
Language:
URL:
https://aclanthology.org/2020.sigtyp-1.3
DOI:
10.18653/v1/2020.sigtyp-1.3
Bibkey:
Cite (ACL):
Alexander Gutkin and Richard Sproat. 2020. NEMO: Frequentist Inference Approach to Constrained Linguistic Typology Feature Prediction in SIGTYP 2020 Shared Task. In Proceedings of the Second Workshop on Computational Research in Linguistic Typology, pages 17–28, Online. Association for Computational Linguistics.
Cite (Informal):
NEMO: Frequentist Inference Approach to Constrained Linguistic Typology Feature Prediction in SIGTYP 2020 Shared Task (Gutkin & Sproat, SIGTYP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.sigtyp-1.3.pdf
Video:
 https://slideslive.com/38939791
Code
 google-research/google-research