Abstract
We explore the task of sentiment analysis on Hinglish (code-mixed Hindi-English) tweets as participants of Task 9 of the SemEval-2020 competition, known as the SentiMix task. We had two main approaches: 1) applying transfer learning by fine-tuning pre-trained BERT models and 2) training feedforward neural networks on bag-of-words representations. During the evaluation phase of the competition, we obtained an F-score of 71.3% with our best model, which placed 4th out of 62 entries in the official system rankings.- Anthology ID:
- 2020.semeval-1.176
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 1304–1309
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.176
- DOI:
- 10.18653/v1/2020.semeval-1.176
- Cite (ACL):
- Vinay Gopalan and Mark Hopkins. 2020. Reed at SemEval-2020 Task 9: Fine-Tuning and Bag-of-Words Approaches to Code-Mixed Sentiment Analysis. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1304–1309, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- Reed at SemEval-2020 Task 9: Fine-Tuning and Bag-of-Words Approaches to Code-Mixed Sentiment Analysis (Gopalan & Hopkins, SemEval 2020)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2020.semeval-1.176.pdf
- Data
- GLUE, SentiMix