Exploiting BERT for End-to-End Aspect-based Sentiment Analysis

Abstract

In this paper, we investigate the modeling power of contextualized embeddings from pre-trained language models, e.g. BERT, on the E2E-ABSA task. Specifically, we build a series of simple yet insightful neural baselines to deal with E2E-ABSA. The experimental results show that even with a simple linear classification layer, our BERT-based architecture can outperform state-of-the-art works. Besides, we also standardize the comparative study by consistently utilizing a hold-out validation dataset for model selection, which is largely ignored by previous works. Therefore, our work can serve as a BERT-based benchmark for E2E-ABSA.

NUT workshop@EMNLP-IJCNLP-2019

References in corpus (14)

• Distributed Representations of Words and Phrases and their Compositionality
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Cross-lingual Language Model Pretraining
• A Structured Self-attentive Sentence Embedding
• Unified Language Model Pre-training for Natural Language Understanding and Generation
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence
• Empower Sequence Labeling with Task-Aware Neural Language Model
• Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification
• Interactive Attention Networks for Aspect-Level Sentiment Classification
• Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis
• Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
• Learning Explicit and Implicit Structures for Targeted Sentiment Analysis
• Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis

Cited by in corpus (7)

• Pre-trained Models for Natural Language Processing: A Survey
• A Benchmark Study of Machine Learning Models for Online Fake News Detection
• Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation
• Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
• DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
• Exploiting BERT to improve aspect-based sentiment analysis performance on Persian language
• Cost-effective Deployment of BERT Models in Serverless Environment