Abstract
Target-oriented sentiment classification aims at classifying sentiment polarities over individual opinion targets in a sentence. RNN with attention seems a good fit for the characteristics of this task, and indeed it achieves the state-of-the-art performance. After re-examining the drawbacks of attention mechanism and the obstacles that block CNN to perform well in this classification task, we propose a new model that achieves new state-of-the-art results on a few benchmarks. Instead of attention, our model employs a CNN layer to extract salient features from the transformed word representations originated from a bi-directional RNN layer. Between the two layers, we propose a component which first generates target-specific representations of words in the sentence, and then incorporates a mechanism for preserving the original contextual information from the RNN layer.- Anthology ID:
- P18-1087
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 946–956
- Language:
- URL:
- https://aclanthology.org/P18-1087
- DOI:
- 10.18653/v1/P18-1087
- Cite (ACL):
- Xin Li, Lidong Bing, Wai Lam, and Bei Shi. 2018. Transformation Networks for Target-Oriented Sentiment Classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 946–956, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Transformation Networks for Target-Oriented Sentiment Classification (Li et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/naacl24-info/P18-1087.pdf
- Code
- lixin4ever/TNet + additional community code
- Data
- SemEval-2014 Task-4