# Embarrassingly Simple Unsupervised Aspect Extraction

Source: [Embarrassingly Simple Unsupervised Aspect Extraction](<https://www.sota2.com/research/paper/68fa676d1e209131cea16219>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T07:43:01.142Z

Authors: St\\'ephan Tulkens, Andreas van Cranenburgh

Published: 2020-04-28T15:09:51.000Z

## Abstract

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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Aspect Extraction on Citysearch 2009 (test)](<https://www.sota2.com/research/sota/aspect-extraction-on-citysearch-2009-test.md>): Aspect Extraction; Citysearch 2009 (test); Precision: 86.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2004.13580>)

[PDF](<https://arxiv.org/pdf/2004.13580.pdf>)

[Implementation](<https://github.com/clips/cat>)