Embarrassingly Simple Unsupervised Aspect Extraction

ACL 2020  ·  Stéphan Tulkens, Andreas van Cranenburgh ·

We present a simple but effective method for aspect identification in sentiment analysis. Our unsupervised method only requires word embeddings and a POS tagger, and is therefore straightforward to apply to new domains and languages. We introduce Contrastive Attention (CAt), a novel single-head attention mechanism based on an RBF kernel, which gives a considerable boost in performance and makes the model interpretable. Previous work relied on syntactic features and complex neural models. We show that given the simplicity of current benchmark datasets for aspect extraction, such complex models are not needed. The code to reproduce the experiments reported in this paper is available at https://github.com/clips/cat

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Aspect Category Detection Citysearch CAt F-measure (%) 86.4 # 1

Methods


No methods listed for this paper. Add relevant methods here