SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling

Ana Marasovic, Anette Frank

Abstract: For over 12 years, machine learning is used to extract opinion-holder-target structures from text to answer the question: Who expressed what kind of sentiment towards what?. However, recent neural approaches do not outperform the state-of-the-art feature-based model for Opinion Role Labelling (ORL). We suspect this is due to the scarcity of labelled training data and address this issue using different multi-task learning techniques with a related task which has substantially more data, i.e. Semantic Role Labelling (SRL). Despite difficulties of the benchmark MPQA corpus, we show that indeed the ORL model benefits from SRL knowledge.