Publication
IWPT 2017
Conference paper

Arc-standard spinal parsing with stack-LSTMs

Abstract

We present a neural transition-based parser for spinal trees, a dependency representation of constituent trees. The parser uses Stack-LSTMs that compose constituent nodes with dependency-based derivations. In experiments, we show that this model adapts to different styles of dependency relations, but this choice has little effect for predicting constituent structure, suggesting that LSTMs induce useful states by themselves.

Date

20 Sep 2017

Publication

IWPT 2017

Authors

Share