Controlled CNN-based Sequence Labeling for Aspect Extraction

TL;DR

This paper introduces a novel controlled CNN model with control modules for supervised aspect extraction, significantly improving performance and preventing overfitting in fine-grained sentiment analysis tasks.

Contribution

It presents the first application of control modules in CNNs for aspect extraction, achieving state-of-the-art results on standard datasets.

Findings

Achieved state-of-the-art performance on aspect extraction datasets

Controlled CNN prevents overfitting effectively

Model significantly boosts CNN performance in sentiment analysis

Abstract

One key task of fine-grained sentiment analysis on reviews is to extract aspects or features that users have expressed opinions on. This paper focuses on supervised aspect extraction using a modified CNN called controlled CNN (Ctrl). The modified CNN has two types of control modules. Through asynchronous parameter updating, it prevents over-fitting and boosts CNN's performance significantly. This model achieves state-of-the-art results on standard aspect extraction datasets. To the best of our knowledge, this is the first paper to apply control modules to aspect extraction.