Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis

TL;DR

This paper introduces a method that uses sentiment-related discourse markers to generate weakly-labeled data, enhancing pretrained language models for sentiment analysis, especially in low-data scenarios, with demonstrated improvements across multiple benchmarks.

Contribution

The paper proposes leveraging sentiment-carrying discourse markers to create large-scale weakly-labeled data for better adaptation of language models to sentiment analysis tasks.

Findings

Improved sentiment analysis performance on benchmark datasets.

Effective adaptation in low-resource settings.

Successful application in finance domain datasets.

Abstract

In recent years, pretrained language models have revolutionized the NLP world, while achieving state of the art performance in various downstream tasks. However, in many cases, these models do not perform well when labeled data is scarce and the model is expected to perform in the zero or few shot setting. Recently, several works have shown that continual pretraining or performing a second phase of pretraining (inter-training) which is better aligned with the downstream task, can lead to improved results, especially in the scarce data setting. Here, we propose to leverage sentiment-carrying discourse markers to generate large-scale weakly-labeled data, which in turn can be used to adapt language models for sentiment analysis. Extensive experimental results show the value of our approach on various benchmark datasets, including the finance domain. Code, models and data are available at https://github.com/ibm/tslm-discourse-markers.