-
Disentangling dialects: a neural approach to Indo-Aryan historical phonology and subgrouping
- Author(s):
- Chundra Cathcart, Taraka Rama
- Date:
- 2020
- Subject(s):
- Computational linguistics, Historical linguistics
- Item Type:
- Conference proceeding
- Conf. Title:
- Conference on Computational Natural Language Learning
- Conf. Org.:
- Special Interest Group on Natural Language Learning (ACL)
- Conf. Loc.:
- Barceló Bávaro Convention Centre, Dominican Republic
- Conf. Date:
- November 19-20, 2020
- Tag(s):
- computational historical linguistics, deep learning, Indo-Aryan, predictions, sound change
- Permanent URL:
- http://dx.doi.org/10.17613/jv1s-3577
- Abstract:
- This paper seeks to uncover patterns of sound change across Indo-Aryan languages using an LSTM encoder-decoder architecture. We augment our models with embeddings representing language ID, part of speech, and other features such as word embeddings. We find that a highly augmented model shows highest accuracy in predicting held-out forms, and investigate other properties of interest learned by our models’ representations. We outline extensions to this architecture that can better capture variation in Indo-Aryan sound change.
- Notes:
- Forthcoming.
- Metadata:
- xml
- Status:
- Published
- Last Updated:
- 1 year ago
- License:
- Attribution-NonCommercial-ShareAlike
conll2020_final.pdf