Zera-Shot Sentiment Analysis for Code-Mixed Data

Code-mixing is the practice of alternating between two or more languages. A major part of sentiment analysis research has been monolingual and they perform poorly on the codemixed text. We introduce methods that use multilingual and cross-lingual embeddings to transfer knowledge from monolingual text to code-mixed text for code-mixed sentiment analysis. Our methods handle code-mixed text through zeroshot learning and beat state-of-the-art English-Spanish codemixed sentiment analysis by an absolute 3% F1-score. We are able to achieve 0. 58 F1-score (without a parallel corpus) and 0. 62 F1-score (with the parallel corpus) on the same benchmark in a zero-shot way as compared to 0. 68 F1score in supervised settings. Our code is publicly available on github. com/sedflix/unsacmt.

Authors

• Siddharth Yadav
• Tanmoy Chakraborty Indian Institute of Technology, Delhi

Keywords

No keywords are indexed for this paper.