Abstract
General-purpose pre-trained word embeddings have become a mainstay of natural language processing, and more recently, methods have been proposed to encode external knowledge into word embeddings to benefit specific downstream tasks. The goal of this paper is to encode sentiment knowledge into pre-trained word vectors to improve the performance of sentiment analysis. Our proposed method is based on a convolutional neural network (CNN) and an external sentiment lexicon. Experiments on four popular sentiment analysis datasets show that this method improves the accuracy of sentiment analysis compared to a number of benchmark methods.- Anthology ID:
- C18-1085
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Emily M. Bender, Leon Derczynski, Pierre Isabelle
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 997–1007
- Language:
- URL:
- https://aclanthology.org/C18-1085
- DOI:
- Cite (ACL):
- Zhe Ye, Fang Li, and Timothy Baldwin. 2018. Encoding Sentiment Information into Word Vectors for Sentiment Analysis. In Proceedings of the 27th International Conference on Computational Linguistics, pages 997–1007, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- Encoding Sentiment Information into Word Vectors for Sentiment Analysis (Ye et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/C18-1085.pdf
- Data
- SST, SST-2