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

TL;DR

CONFLATOR introduces a novel positional encoding method that emphasizes switching points in code-mixed language modeling, significantly improving performance on sentiment analysis and translation tasks for Hinglish.

Contribution

The paper proposes CONFLATOR, a neural language model that incorporates switching point information with rotatory positional encodings for better code-mixed language understanding.

Findings

Outperforms state-of-the-art on Hinglish sentiment analysis

Achieves superior results in Hinglish machine translation

Effective encoding of switching points enhances model performance

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.