CLSep 4, 2019

Extracting Aspects Hierarchies using Rhetorical Structure Theory

arXiv:1909.01800v11 citations
Originality Incremental advance
AI Analysis

This addresses the need for hierarchical aspect extraction in natural language processing, enabling finer-grained sentiment analysis, though it appears incremental in its technical approach.

The paper tackled the problem of generating aspect hierarchies from text, proposing an unsupervised method using Rhetorical Structure Theory and graph analysis, and achieved 80% coverage compared to human-generated hierarchies on 100,000 Amazon reviews.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes