Abstract
Neural models have been investigated for sentiment classification over constituent trees. They learn phrase composition automatically by encoding tree structures but do not explicitly model sentiment composition, which requires to encode sentiment class labels. To this end, we investigate two formalisms with deep sentiment representations that capture sentiment subtype expressions by latent variables and Gaussian mixture vectors, respectively. Experiments on Stanford Sentiment Treebank (SST) show the effectiveness of sentiment grammar over vanilla neural encoders. Using ELMo embeddings, our method gives the best results on this benchmark.- Anthology ID:
- P19-1457
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4642–4651
- Language:
- URL:
- https://aclanthology.org/P19-1457
- DOI:
- 10.18653/v1/P19-1457
- Cite (ACL):
- Liwen Zhang, Kewei Tu, and Yue Zhang. 2019. Latent Variable Sentiment Grammar. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4642–4651, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Latent Variable Sentiment Grammar (Zhang et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/P19-1457.pdf
- Code
- Ehaschia/bi-tree-lstm-crf
- Data
- SST, SST-2, SST-5