Publication Type

Journal Article

Version

acceptedVersion

Publication Date

1-2019

Abstract

Extracting aspect terms and opinion terms are two fundamental tasks in opinion mining. The recent success of deep learning has inspired various neural network architectures, which have been shown to achieve highly competitive performance in these two tasks. However, most existing methods fail to explicitly consider the syntactic relations among aspect terms and opinion terms, which may lead to the inconsistencies between the model predictions and the syntactic constraints. To this end, we first apply a multi-task learning framework to implicitly capture the relations between the two tasks, and then propose a global inference method by explicitly modelling several syntactic constraints among aspect term extraction and opinion term extraction to uncover their intra-task and inter-task relationship, which seeks an optimal solution over the neural predictions for both tasks. Extensive evaluations on three benchmark datasets demonstrate that our global inference approach is able to bring consistent improvements over several base models in different scenarios.

Keywords

Benchmark testing, Labeling, Natural language processing, Neural networks, Neural networks, Opinion mining, Sentiment analysis, Sentiment analysis, Standards, Syntactics, Task analysis

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

IEEE/ACM Transactions on Audio, Speech and Language Processing

Volume

27

Issue

1

First Page

168

Last Page

177

ISSN

2329-9290

Identifier

10.1109/TASLP.2018.2875170

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/TASLP.2018.2875170

Download

Share

COinS