Abstract
Generic word embeddings are trained on large-scale generic corpora; Domain Specific (DS) word embeddings are trained only on data from a domain of interest. This paper proposes a method to combine the breadth of generic embeddings with the specificity of domain specific embeddings. The resulting embeddings, called Domain Adapted (DA) word embeddings, are formed by aligning corresponding word vectors using Canonical Correlation Analysis (CCA) or the related nonlinear Kernel CCA. Evaluation results on sentiment classification tasks show that the DA embeddings substantially outperform both generic, DS embeddings when used as input features to standard or state-of-the-art sentence encoding algorithms for classification.- Anthology ID:
- P18-2007
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 37–42
- Language:
- URL:
- https://aclanthology.org/P18-2007
- DOI:
- 10.18653/v1/P18-2007
- Cite (ACL):
- Prathusha K Sarma, Yingyu Liang, and Bill Sethares. 2018. Domain Adapted Word Embeddings for Improved Sentiment Classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 37–42, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Domain Adapted Word Embeddings for Improved Sentiment Classification (K Sarma et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/P18-2007.pdf