Published:
2020-06-02
Proceedings:
Proceedings of the AAAI Conference on Artificial Intelligence, 34
Volume
Issue:
Vol. 34 No. 10: Issue 10: AAAI-20 Student Tracks
Track:
Student Abstract Track
Downloads:
Abstract:
Aspect term extraction is a fundamental task for aspect-level sentiment analysis. Previous methods tend to extract noun aspect terms due to the large quantities of them, and perform badly on extracting aspect terms containing words with other POS tags, according to experimental results. In addition, few works focus on the POS tags of adjacent words which are critical to aspect term extraction. We propose a novel model which combines POS and word features in an interactive way, and makes full use of the POS tags of adjacent words by POS window. We conduct experiments on two datasets, and prove the effectiveness of our model.
DOI:
10.1609/aaai.v34i10.7261
AAAI
Vol. 34 No. 10: Issue 10: AAAI-20 Student Tracks
ISSN 2374-3468 (Online) ISSN 2159-5399 (Print) ISBN 978-1-57735-835-0 (10 issue set)
Published by AAAI Press, Palo Alto, California USA Copyright © 2020, Association for the Advancement of Artificial Intelligence All Rights Reserved