Aspect Based Sentiment Analysis with Aspect-Specific Opinion Spans

EMNLP 2020  ·  Lu Xu, Lidong Bing, Wei Lu, Fei Huang ·

Aspect based sentiment analysis, predicting sentiment polarity of given aspects, has drawn extensive attention. Previous attention-based models emphasize using aspect semantics to help extract opinion features for classification. However, these works are either not able to capture opinion spans as a whole, or not able to capture variable-length opinion spans. In this paper, we present a neat and effective structured attention model by aggregating multiple linear-chain CRFs. Such a design allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features. The experimental results on four datasets demonstrate the effectiveness of the proposed model, and our analysis demonstrates that our model can capture aspect-specific opinion spans.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Aspect-Based Sentiment Analysis (ABSA) SemEval 2014 Task 4 Sub Task 2 MCRF-SA Restaurant (Acc) 82.86 # 17
Laptop (Acc) 77.64 # 15
Mean Acc (Restaurant + Laptop) 80.25 # 15


No methods listed for this paper. Add relevant methods here