Lock-Free Parallel Perceptron for Graph-based Dependency Parsing

03/02/2017
by   Xu Sun, et al.
0

Dependency parsing is an important NLP task. A popular approach for dependency parsing is structured perceptron. Still, graph-based dependency parsing has the time complexity of O(n^3), and it suffers from slow training. To deal with this problem, we propose a parallel algorithm called parallel perceptron. The parallel algorithm can make full use of a multi-core computer which saves a lot of training time. Based on experiments we observe that dependency parsing with parallel perceptron can achieve 8-fold faster training speed than traditional structured perceptron methods when using 10 threads, and with no loss at all in accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/22/2020

Transition-Based Dependency Parsing using Perceptron Learner

Syntactic parsing using dependency structures has become a standard tech...
research
10/10/2020

Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training

In this paper, we propose second-order graph-based neural dependency par...
research
06/19/2015

Structured Training for Neural Network Transition-Based Parsing

We present structured perceptron training for neural network transition-...
research
08/12/2021

Combining (second-order) graph-based and headed span-based projective dependency parsing

Graph-based methods are popular in dependency parsing for decades. Recen...
research
05/09/2023

Structured Sentiment Analysis as Transition-based Dependency Parsing

Structured sentiment analysis (SSA) aims to automatically extract people...
research
07/11/2018

UniParse: A universal graph-based parsing toolkit

This paper describes the design and use of the graph-based parsing frame...
research
06/15/2021

Maximum Spanning Trees Are Invariant to Temperature Scaling in Graph-based Dependency Parsing

Modern graph-based syntactic dependency parsers operate by predicting, f...

Please sign up or login with your details

Forgot password? Click here to reset