Abstract

Open-domain targeted sentiment analysis aims to detect opinion targets along with their sentiment polarities from a sentence. Prior work typically formulates this task as a sequence tagging problem. However, such formulation suffers from problems such as huge search space and sentiment inconsistency. To address these problems, we propose a span-based extract-then-classify framework, where multiple opinion targets are directly extracted from the sentence under the supervision of target span boundaries, and corresponding polarities are then classified using their span representations. We further investigate three approaches under this framework, namely the pipeline, joint, and collapsed models. Experiments on three benchmark datasets show that our approach consistently outperforms the sequence tagging baseline. Moreover, we find that the pipeline model achieves the best performance compared with the other two models.

Highlights

  • Open-domain targeted sentiment analysis is a fundamental task in opinion mining and sentiment analysis (Pang et al, 2008; Liu, 2012)

  • Since opinion targets are not given, we need to first detect the targets from the input text. This subtask, which is usually denoted as target extraction, can be solved by sequence tagging methods (Jakob and Gurevych, 2010; Liu et al, 2015; Wang et al, 2016a; Poria et al, 2016; Shu et al, 2017; He et al, 2017; Xu et al, 2018)

  • Instead of formulating the open-domain targeted sentiment analysis task as a sequence tagging problem, we propose to use a span-based labeling scheme as follows: given an input sentence x = (x1, ..., xn) with length n, and a target list T = {t1, ..., tm}, where the number of targets is m and each target ti is annotated with its start position, its end position, and its sentiment polarity

Read more

Summary

Introduction

Open-domain targeted sentiment analysis is a fundamental task in opinion mining and sentiment analysis (Pang et al, 2008; Liu, 2012). Targets: Windows 7, Vista Polarities: positive, negative. Since opinion targets are not given, we need to first detect the targets from the input text. This subtask, which is usually denoted as target extraction, can be solved by sequence tagging methods (Jakob and Gurevych, 2010; Liu et al, 2015; Wang et al, 2016a; Poria et al, 2016; Shu et al, 2017; He et al, 2017; Xu et al, 2018). Lots of efforts have been made to design sophisticated classifiers for this subtask, they all assume that the targets are already given

Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.