Implicit Syntactic Features for Target-dependent Sentiment Analysis

Yuze Gao, Yue Zhang, Tong Xiao


Abstract
Targeted sentiment analysis investigates the sentiment polarities on given target mentions from input texts. Different from sentence level sentiment, it offers more fine-grained knowledge on each entity mention. While early work leveraged syntactic information, recent research has used neural representation learning to induce features automatically, thereby avoiding error propagation of syntactic parsers, which are particularly severe on social media texts. We study a method to leverage syntactic information without explicitly building the parser outputs, by training an encoder-decoder structure parser model on standard syntactic treebanks, and then leveraging its hidden encoder layers when analysing tweets. Such hidden vectors do not contain explicit syntactic outputs, yet encode rich syntactic features. We use them to augment the inputs to a baseline state-of-the-art targeted sentiment classifier, observing significant improvements on various benchmark datasets. We obtain the best accuracies on all test sets.
Anthology ID:
I17-1052
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
516–524
Language:
URL:
https://aclanthology.org/I17-1052
DOI:
Bibkey:
Cite (ACL):
Yuze Gao, Yue Zhang, and Tong Xiao. 2017. Implicit Syntactic Features for Target-dependent Sentiment Analysis. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 516–524, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Implicit Syntactic Features for Target-dependent Sentiment Analysis (Gao et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/I17-1052.pdf