Extended Dependency-Based Word Embeddings for Aspect Extraction
Extracting aspects from opinion reviews is an essential task of fine-grained sentiment analysis. In this paper, we introduce outer product of dependency-based word vectors and specialized features as representation of words. With such extended embeddings composed in recurrent neural networks, we make use of advantages of both word embeddings and traditional features. Evaluated on SemEval 2014 task 4 dataset, the proposed method outperform existing recurrent models based methods, achieving a result comparable with the state-of-the-art method. It shows that it is an effective way to achieve better extraction performance by improving word representations.
KeywordsAspect extraction Sequence labelling Sentiment analysis Word embeddings Representation learning
This work is supported by the projects of China Postdoctoral Science Special Foundation (No. 2014T70340), National Natural Science Foundation of China (No. 61300114 and No. 61572151), and Specialized Research Fund for the Doctoral Program of Higher Education (No. 20132302120047).
- 1.Chernyshevich, M.: IHS R&D belarus: Cross-domain extraction of product features using conditional random fields. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 309–313 (2014)Google Scholar
- 4.Graves, A.: RNNLIB: a recurrent neural network library for sequence learning problems (2010). http://sourceforge.net/projects/rnnl
- 5.Irsoy, O., Cardie, C.: Opinion mining with deep recurrent neural networks. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 720–728 (2014)Google Scholar
- 6.İrsoy, O., Cardie, C.: Modeling compositionality with multiplicative recurrent neural networks. In: International Conference on Learning Representations (ICLR) (2015)Google Scholar
- 7.Levy, O., Goldberg, Y.: Dependency-based word embeddings. In: ACL (2), pp. 302–308 (2014)Google Scholar
- 8.Liu, P., Joty, S., Meng, H.: Fine-grained opinion mining with recurrent neural networks and word embeddings. In: Conference on Empirical Methods in Natural Language Processing (EMNLP 2015) (2015)Google Scholar
- 9.Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)Google Scholar
- 10.Pontiki, M., Galanis, D., Pavlopoulos, J., Papageorgiou, H., Androutsopoulos, I., Manandhar, S.: Semeval-2014 task 4: aspect based sentiment analysis. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 27–35 (2014)Google Scholar
- 11.Ramshaw, L.A., Marcus, M.P.: Text chunking using transformation-based learning. In: Third Workshop on Very Large Corpora (1995)Google Scholar
- 12.Toh, Z., Wang, W.: DLIREC: aspect term extraction and term polarity classification system. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 235–240 (2014)Google Scholar
- 13.Yu, M., Gormley, M.R., Dredze, M.: Combining word embeddings and feature embeddings for fine-grained relation extraction. In: North American Chapter of the Association for Computational Linguistics (NAACL) (2015)Google Scholar