SRL4ORL: Improving Opinion Role Labeling using Multi-task Learning with Semantic Role Labeling

TL;DR

This paper enhances Opinion Role Labeling by employing multi-task learning with Semantic Role Labeling, leveraging more data to improve the extraction of opinion-holder-target structures.

Contribution

It introduces multi-task learning models that significantly improve ORL performance by utilizing SRL data, addressing data scarcity issues in opinion analysis.

Findings

Multi-task learning improves ORL accuracy.

Vanilla MTL model performs best among tested approaches.

Deeper analysis suggests avenues for further improvements.

Abstract

For over a decade, machine learning has been used to extract opinion-holder-target structures from text to answer the question "Who expressed what kind of sentiment towards what?". Recent neural approaches do not outperform the state-of-the-art feature-based models for Opinion Role Labeling (ORL). We suspect this is due to the scarcity of labeled training data and address this issue using different multi-task learning (MTL) techniques with a related task which has substantially more data, i.e. Semantic Role Labeling (SRL). We show that two MTL models improve significantly over the single-task model for labeling of both holders and targets, on the development and the test sets. We found that the vanilla MTL model which makes predictions using only shared ORL and SRL features, performs the best. With deeper analysis we determine what works and what might be done to make further improvements for ORL.