SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token

IKHYUN CHO, Yoonhwa Jung, Julia Hockenmaier

Submission Type: Regular Long Paper

Submission Track: Efficient Methods for NLP

Submission Track 2: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Keywords: Aspect-based sentiment analysis, Pre-trained Language Models, RoBERTa

TL;DR: A syntax-integrated RoBERTa-based model for aspect-based sentiment analysis.

Abstract: We present a simple, but effective method to incorporate syntactic dependency information directly into transformer-based language models (e.g. RoBERTa) for tasks such as Aspect-Based Sentiment Classification (ABSC), where the desired output depends on specific input tokens. In contrast to prior approaches to ABSC that capture syntax by combining language models with graph neural networks over dependency trees, our model, Syntax-Integrated RoBERTa for ABSC (SIR-ABSC) incorporates syntax directly into the language model by using a novel aggregator token. Yet, SIR-ABSC outperforms these more complex models, yielding new state-of-the-art results on ABSC.

Submission Number: 2852