Cross-lingual Semantic Role Labelling with the Valpal database knowledge

AbstractCross-lingual Transfer Learning typically involves training a model on a high-resource source language and applying it to a low-resource target language. In this work we introduce a lexical database called Valency Patterns Leipzig (ValPal) which provides the argument pattern information about various verb-forms in multiple languages including low-resource languages. We also provide a framework to integrate the ValPal database knowledge into the state-of-the-art LSTM based model for cross-lingual semantic role labelling. Experimental results show that integrating such knowledge resulted in am improvement in performance of the model on all the target languages on which it is evaluated.