Left-to-Right Dependency Parsing with Pointer Networks

We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building n attachments, with n being the length of the input sentence. Similarly to the recent stack-pointer parser by Ma et al. (2018), we use the pointer network framework that, given a word, can directly point to a position from the sentence. However, our left-to-right approach is simpler than the original top-down stack-pointer parser (not requiring a stack) and reduces transition sequence length in half, from 2n-1 actions to n. This results in a quadratic non-projective parser that runs twice as fast as the original while achieving the best accuracy to date on the English PTB dataset (96.04 single-model dependency parsers, and improves over the former top-down transition system in the majority of languages tested.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/03/2018

Stack-Pointer Networks for Dependency Parsing

We introduce a novel architecture for dependency parsing: stack-pointer ...
research
05/20/2021

Dependency Parsing with Bottom-up Hierarchical Pointer Networks

Dependency parsing is a crucial step towards deep language understanding...
research
03/11/2016

Training with Exploration Improves a Greedy Stack-LSTM Parser

We adapt the greedy Stack-LSTM dependency parser of Dyer et al. (2015) t...
research
04/29/2021

AMR Parsing with Action-Pointer Transformer

Abstract Meaning Representation parsing is a sentence-to-graph predictio...
research
05/23/2018

A Transition-based Algorithm for Unrestricted AMR Parsing

Non-projective parsing can be useful to handle cycles and reentrancy in ...
research
03/19/2016

A Fast Unified Model for Parsing and Sentence Understanding

Tree-structured neural networks exploit valuable syntactic parse informa...
research
05/31/2019

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

Our work involves enriching the Stack-LSTM transition-based AMR parser (...

Please sign up or login with your details

Forgot password? Click here to reset