An Integrated Semantic-Syntactic SBLSTM Model for Aspect Specific Opinion Extraction

Zhongming Han, Xin Jiang, Mengqi Li, Mengmei Zhang, Dagao DuanWISA 2018 · OpenReview

Abstract

Opinion Mining (OM) of Internet reviews is one of the key issues in Natural Language Processing (NLP) field. This paper proposes a stacked Bi-LSTM aspect opinion extraction model in which semantic and syntactic features are both integrated. The model takes embedded vector which is composed by word embedding, POS tags and dependency relations as its input while taking label sequence as its output. The experimental results show the effectiveness of this structural features embedded stacked Bi-LSTM model on cross-domain and cross-language datasets, and indicate that this model outperforms the state-of-the-art methods.
BibTeX
@inproceedings{han2018integrated,
  author = {Zhongming Han and Xin Jiang and Mengqi Li and Mengmei Zhang and Dagao Duan},
  title = {{An Integrated Semantic-Syntactic SBLSTM Model for Aspect Specific Opinion Extraction}},
  booktitle = {WISA},
  year = {2018},
  url = {https://openreview.net/forum?id=PzAzRXJunz},
}

Loading related content...

Figure