Simpler but More Accurate Semantic Dependency Parsing
Timothy Dozat, Christopher D. Manning · 2018
While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture betweenword 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 stateof-the-art performance, beating the previous, substantially more complex stateof-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.