Abstract
The success of sentence classification often depends on understanding both the syntactic and semantic properties of word-phrases. Recent progress on this task has been based on exploiting the grammatical structure of sentences but often this structure is difficult to parse and noisy. In this paper, we propose a structure-independent ‘Gated Representation Alignment’ (GRA) model that blends a phrase-focused Convolutional Neural Network (CNN) approach with sequence-oriented Recurrent Neural Network (RNN). Our novel alignment mechanism allows the RNN to selectively include phrase information in a word-by-word sentence representation, and to do this without awareness of the syntactic structure. An empirical evaluation of GRA shows higher prediction accuracy (up to 4.6%) of fine-grained sentiment ratings, when compared to other structure-independent baselines. We also show comparable results to several structure-dependent methods. Finally, we analyzed the effect of our alignment mechanism and found that this is critical to the effectiveness of the CNN-RNN hybrid.- Anthology ID:
- E17-2071
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Mirella Lapata, Phil Blunsom, Alexander Koller
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 443–449
- Language:
- URL:
- https://aclanthology.org/E17-2071
- DOI:
- Cite (ACL):
- Shiou Tian Hsu, Changsung Moon, Paul Jones, and Nagiza Samatova. 2017. A Hybrid CNN-RNN Alignment Model for Phrase-Aware Sentence Classification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 443–449, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- A Hybrid CNN-RNN Alignment Model for Phrase-Aware Sentence Classification (Hsu et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/E17-2071.pdf
- Data
- SST, SST-2, SST-5