Dependency parsing is a crucial step towards deep language understanding . Left-to-right and top-down transition-based algorithms that rely on Pointer Networks are among the most accurate approaches to performing dependency parsing . We develop a bottom-up-oriented HierarchicalPointer Network for the left-to the-right parser . We propose two novel novel noveltransition-based alternatives: an approach that parses a sentence in right-to left order and a variant that does it from the outside in . Weempirically test the proposed neural architecture with the different algorithms on a wide variety of languages, outperforming the original approach inpractically all of them . We set new state-of-the-art results on the Englishand Chinese Penn Treebanks for non-contextualized and BERT-based embeddings

Author(s) : Daniel Fernández-González, Carlos Gómez-Rodríguez

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : left - parsing - dependency - based - approach -

Leave a Reply

Your email address will not be published. Required fields are marked *