papers AI Learner
The Github is limit! Click to go to the new site.

Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis

2018-04-30
Fei Liu, Trevor Cohn, Timothy Baldwin

Abstract

While neural networks have been shown to achieve impressive results for sentence-level sentiment analysis, targeted aspect-based sentiment analysis (TABSA) — extraction of fine-grained opinion polarity w.r.t. a pre-defined set of aspects — remains a difficult task. Motivated by recent advances in memory-augmented models for machine reading, we propose a novel architecture, utilising external “memory chains” with a delayed memory update mechanism to track entities. On a TABSA task, the proposed model demonstrates substantial improvements over state-of-the-art approaches, including those using external knowledge bases.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1804.11019

PDF

https://arxiv.org/pdf/1804.11019


Similar Posts

Comments