Extracting Aspects Hierarchies using Rhetorical Structure Theory
Computation and Language
2019-09-05 v1
Abstract
We propose a novel approach to generate aspect hierarchies that proved to be consistently correct compared with human-generated hierarchies. We present an unsupervised technique using Rhetorical Structure Theory and graph analysis. We evaluated our approach based on 100,000 reviews from Amazon and achieved an astonishing 80% coverage compared with human-generated hierarchies coded in ConceptNet. The method could be easily extended with a sentiment analysis model and used to describe sentiment on different levels of aspect granularity. Hence, besides the flat aspect structure, we can differentiate between aspects and describe if the charging aspect is related to battery or price.
Cite
@article{arxiv.1909.01800,
title = {Extracting Aspects Hierarchies using Rhetorical Structure Theory},
author = {Łukasz Augustyniak and Tomasz Kajdanowicz and Przemysław Kazienko},
journal= {arXiv preprint arXiv:1909.01800},
year = {2019}
}
Comments
ACAI 2018 MLNLP