Simpler but More Accurate Semantic Dependency Parsing

Code

• github.com/yzhangcs/parser
  pytorch★ 878
• gitlab.com/ucdavisnlp/dialog-parsing
  tf★ 0
• github.com/tdozat/Parser-v3
  tf★ 0

Abstract

While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, using graph-structured representations. We extend the LSTM-based syntactic parser of Dozat and Manning (2017) to train on and generate these graph structures. The resulting system on its own achieves state-of-the-art performance, beating the previous, substantially more complex state-of-the-art system by 0.6% labeled F1. Adding linguistically richer input representations pushes the margin even higher, allowing us to beat it by 1.9% labeled F1.

Tasks

Reproductions