Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction

About

This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction. The former task is to extract aspects of a product or service from an opinion document, and the latter is to identify the polarity expressed in the document about these extracted aspects. Most existing algorithms address them as two separate tasks and solve them one by one, or only perform one task, which can be complicated for real applications. In this paper, we treat these two tasks as two sequence labeling problems and propose a novel Dual crOss-sharEd RNN framework (DOER) to generate all aspect term-polarity pairs of the input sentence simultaneously. Specifically, DOER involves a dual recurrent neural network to extract the respective representation of each task, and a cross-shared unit to consider the relationship between them. Experimental results demonstrate that the proposed framework outperforms state-of-the-art baselines on three benchmark datasets.

Huaishao Luo, Tianrui Li, Bing Liu, Junbo Zhang• 2019

Related benchmarks

TaskDatasetResultRank
Aspect-Term Sentiment AnalysisLAPTOP SemEval 2014 (test)
Macro-F160.35
69
Aspect ExtractionLaptop (test)
F1 Score82.61
30
Aspect term-polarity pair extractionSemEval Restaurant (SR) (test)
F1 Score72.78
29
Aspect term-polarity pair extractionSemEval Laptop (SL) (test)
F1 Score0.6035
28
Aspect term-polarity pair extractionTwitter ST (test)
F1 Score51.37
18
Aspect-based Sentiment AnalysisREST 2014 (test)
ABSA F1 Score68.55
15
Aspect-based Sentiment AnalysisLAP 2014 (test)
ABSA-F156.71
15
Aspect-based Sentiment AnalysisREST 2015 (test)
ABSA-F10.5031
15
End-to-End Aspect-Based Sentiment AnalysisREST SemEval 2015 2016 (test)
F1 Score72.78
10
Aspect Term ExtractionDR Restaurant SemEval 2014 (test)
F1 Score81.06
10
Showing 10 of 17 rows

Other info

Code

Follow for update