CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling

Mohsin Mohammed, Sai Kandukuri, Neeharika Gupta, Parth Patwa, Anubhab Chatterjee, Vinija Jain, Aman Chadha, Amitava Das


Abstract
The mixing of two or more languages is called Code-Mixing (CM). CM is a social norm in multilingual societies. Neural Language Models (NLMs) like transformers have been effective on many NLP tasks. However, NLM for CM is an under-explored area. Though transformers are capable and powerful, they cannot always encode positional information since they are non-recurrent. Therefore, to enrich word information and incorporate positional information, positional encoding is defined. We hypothesize that Switching Points (SPs), i.e., junctions in the text where the language switches (L1 -> L2 or L2 -> L1), pose a challenge for CM Language Models (LMs), and hence give special emphasis to SPs in the modeling process. We experiment with several positional encoding mechanisms and show that rotatory positional encodings along with switching point information yield the best results.We introduce CONFLATOR: a neural language modeling approach for code-mixed languages. CONFLATOR tries to learn to emphasize switching points using smarter positional encoding, both at unigram and bigram levels. CONFLATOR outperforms the state-of-the-art on two tasks based on code-mixed Hindi and English (Hinglish): (i) sentiment analysis and (ii) machine translation.
Anthology ID:
2023.calcs-1.6
Volume:
Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching
Month:
December
Year:
2023
Address:
Singapore
Editors:
Genta Winata, Sudipta Kar, Marina Zhukova, Thamar Solorio, Mona Diab, Sunayana Sitaram, Monojit Choudhury, Kalika Bali
Venues:
CALCS | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–73
Language:
URL:
https://aclanthology.org/2023.calcs-1.6
DOI:
10.18653/v1/2023.calcs-1.6
Bibkey:
Cite (ACL):
Mohsin Mohammed, Sai Kandukuri, Neeharika Gupta, Parth Patwa, Anubhab Chatterjee, Vinija Jain, Aman Chadha, and Amitava Das. 2023. CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling. In Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching, pages 64–73, Singapore. Association for Computational Linguistics.
Cite (Informal):
CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling (Mohammed et al., CALCS-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.calcs-1.6.pdf