Abstract
This paper describes our contribution to the SemEval-2020 Task 9 on Sentiment Analysis for Code-mixed Social Media Text. We investigated two approaches to solve the task of Hinglish sentiment analysis. The first approach uses cross-lingual embeddings resulting from projecting Hinglish and pre-trained English FastText word embeddings in the same space. The second approach incorporates pre-trained English embeddings that are incrementally retrained with a set of Hinglish tweets. The results show that the second approach performs best, with an F1-score of 70.52% on the held-out test data.- Anthology ID:
- 2020.semeval-1.173
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 1288–1293
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.173
- DOI:
- 10.18653/v1/2020.semeval-1.173
- Cite (ACL):
- Pranaydeep Singh and Els Lefever. 2020. LT3 at SemEval-2020 Task 9: Cross-lingual Embeddings for Sentiment Analysis of Hinglish Social Media Text. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1288–1293, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- LT3 at SemEval-2020 Task 9: Cross-lingual Embeddings for Sentiment Analysis of Hinglish Social Media Text (Singh & Lefever, SemEval 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.semeval-1.173.pdf