Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis

Abstract

In aspect-based sentiment analysis, extracting aspect terms along with the opinions being expressed from user-generated content is one of the most important subtasks. Previous studies have shown that exploiting connections between aspect and opinion terms is promising for this task. In this paper, we propose a novel joint model that integrates recursive neural networks and conditional random fields into a unified framework for explicit aspect and opinion terms co-extraction. The proposed model learns high-level discriminative features and double propagate information between aspect and opinion terms, simultaneously. Moreover, it is flexible to incorporate hand-crafted features into the proposed model to further boost its information extraction performance. Experimental results on the SemEval Challenge 2014 dataset show the superiority of our proposed model over several baseline methods as well as the winning systems of the challenge.

References in corpus (1)

• A Convolutional Neural Network for Modelling Sentences

Cited by in corpus (10)

• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
• Relational Graph Attention Network for Aspect-based Sentiment Analysis
• A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis
• Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
• Controlled CNN-based Sequence Labeling for Aspect Extraction
• DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
• Improving Aspect-Level Sentiment Analysis with Aspect Extraction
• Aspect-Sentiment-Multiple-Opinion Triplet Extraction
• Aspect Sentiment Model for Micro Reviews