How to best use Syntax in Semantic Role Labelling
This work addresses the challenge of integrating external syntactic data into SRL models for NLP researchers, though it is incremental as it builds on existing neural models.
The paper tackled the problem of effectively using syntactic information in Semantic Role Labeling (SRL) by evaluating different encoding and injection methods, resulting in a new state-of-the-art for non-ensemble models on CoNLL'05 and CoNLL'12 benchmarks.
There are many different ways in which external information might be used in an NLP task. This paper investigates how external syntactic information can be used most effectively in the Semantic Role Labeling (SRL) task. We evaluate three different ways of encoding syntactic parses and three different ways of injecting them into a state-of-the-art neural ELMo-based SRL sequence labelling model. We show that using a constituency representation as input features improves performance the most, achieving a new state-of-the-art for non-ensemble SRL models on the in-domain CoNLL'05 and CoNLL'12 benchmarks.