What can we learn from Semantic Tagging?

• DOI: 10.18653/v1/d18-1526
• Publication Date: 2019-06-29T16:01:17Z
• Authors: Mostafa Abdou; Artur Kulmizev; Vinit Ravishankar; Lasha Abzianidze; Johan Bos
• Keywords: Transfer of learning; Dependency grammar

We investigate the effects of multi-task learning using recently introduced task semantic tagging. employ tagging as an auxiliary for three different NLP tasks: part-of-speech tagging, Universal Dependency parsing, and Natural Language Inference. compare full neural network sharing, partial what we term to share setting where negative transfer between tasks is less likely. Our findings show considerable improvements all tasks, particularly in which shows consistent gains across tasks.