Abstract
In this paper, we explore the methods of obtaining parse trees of code-mixed sentences and analyse the obtained trees. Existing work has shown that linguistic theories can be used to generate code-mixed sentences from a set of parallel sentences. We build upon this work, using one of these theories, the Equivalence-Constraint theory to obtain the parse trees of synthetically generated code-mixed sentences and evaluate them with a neural constituency parser. We highlight the lack of a dataset non-synthetic code-mixed constituency parse trees and how it makes our evaluation difficult. To complete our evaluation, we convert a code-mixed dependency parse tree set into “pseudo constituency trees” and find that a parser trained on synthetically generated trees is able to decently parse these as well.- Anthology ID:
- 2020.calcs-1.8
- Volume:
- Proceedings of the 4th Workshop on Computational Approaches to Code Switching
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Editors:
- Thamar Solorio, Monojit Choudhury, Kalika Bali, Sunayana Sitaram, Amitava Das, Mona Diab
- Venue:
- CALCS
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 57–64
- Language:
- English
- URL:
- https://aclanthology.org/2020.calcs-1.8
- DOI:
- Cite (ACL):
- Anirudh Srinivasan, Sandipan Dandapat, and Monojit Choudhury. 2020. Code-mixed parse trees and how to find them. In Proceedings of the 4th Workshop on Computational Approaches to Code Switching, pages 57–64, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Code-mixed parse trees and how to find them (Srinivasan et al., CALCS 2020)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2020.calcs-1.8.pdf