MSR India at SemEval-2020 Task 9: Multilingual Models Can Do Code-Mixing Too

Anirudh Srinivasan


Abstract
In this paper, we present our system for the SemEval 2020 task on code-mixed sentiment analysis. Our system makes use of large transformer based multilingual embeddings like mBERT. Recent work has shown that these models posses the ability to solve code-mixed tasks in addition to their originally demonstrated cross-lingual abilities. We evaluate the stock versions of these models for the sentiment analysis task and also show that their performance can be improved by using unlabelled code-mixed data. Our submission (username Genius1237) achieved the second rank on the English-Hindi subtask with an F1 score of 0.726.
Anthology ID:
2020.semeval-1.122
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Editors:
Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
Venue:
SemEval
SIG:
SIGLEX
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
951–956
Language:
URL:
https://aclanthology.org/2020.semeval-1.122
DOI:
10.18653/v1/2020.semeval-1.122
Bibkey:
Cite (ACL):
Anirudh Srinivasan. 2020. MSR India at SemEval-2020 Task 9: Multilingual Models Can Do Code-Mixing Too. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 951–956, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
MSR India at SemEval-2020 Task 9: Multilingual Models Can Do Code-Mixing Too (Srinivasan, SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.122.pdf