An Unsupervised Neural Attention Model for Aspect Extraction

Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier


Abstract
Aspect extraction is an important and challenging task in aspect-based sentiment analysis. Existing works tend to apply variants of topic models on this task. While fairly successful, these methods usually do not produce highly coherent aspects. In this paper, we present a novel neural approach with the aim of discovering coherent aspects. The model improves coherence by exploiting the distribution of word co-occurrences through the use of neural word embeddings. Unlike topic models which typically assume independently generated words, word embedding models encourage words that appear in similar contexts to be located close to each other in the embedding space. In addition, we use an attention mechanism to de-emphasize irrelevant words during training, further improving the coherence of aspects. Experimental results on real-life datasets demonstrate that our approach discovers more meaningful and coherent aspects, and substantially outperforms baseline methods on several evaluation tasks.
Anthology ID:
P17-1036
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
388–397
Language:
URL:
https://aclanthology.org/P17-1036
DOI:
10.18653/v1/P17-1036
Bibkey:
Cite (ACL):
Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2017. An Unsupervised Neural Attention Model for Aspect Extraction. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 388–397, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
An Unsupervised Neural Attention Model for Aspect Extraction (He et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1036.pdf
Video:
 https://vimeo.com/234952560
Code
 ruidan/Unsupervised-Aspect-Extraction +  additional community code