Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses

04/17/2018
by   Katherine A. Keith, et al.
0

Dependency parsing research, which has made significant gains in recent years, typically focuses on improving the accuracy of single-tree predictions. However, ambiguity is inherent to natural language syntax, and communicating such ambiguity is important for error analysis and better-informed downstream applications. In this work, we propose a transition sampling algorithm to sample from the full joint distribution of parse trees defined by a transition-based parsing model, and demonstrate the use of the samples in probabilistic dependency analysis. First, we define the new task of dependency path prediction, inferring syntactic substructures over part of a sentence, and provide the first analysis of performance on this task. Second, we demonstrate the usefulness of our Monte Carlo syntax marginal method for parser error analysis and calibration. Finally, we use this method to propagate parse uncertainty to two downstream information extraction applications: identifying persons killed by police and semantic role assignment.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/28/2012

Elimination of Spurious Ambiguity in Transition-Based Dependency Parsing

We present a novel technique to remove spurious ambiguity from transitio...
research
11/28/2017

Hybrid Oracle: Making Use of Ambiguity in Transition-based Chinese Dependency Parsing

In the training of transition-based dependency parsers, an oracle is use...
research
10/04/2020

A Survey of Unsupervised Dependency Parsing

Syntactic dependency parsing is an important task in natural language pr...
research
10/04/2018

Monte Carlo Dependency Estimation

Estimating the dependency of variables is a fundamental task in data ana...
research
12/25/2021

Combining Improvements for Exploiting Dependency Trees in Neural Semantic Parsing

The dependency tree of a natural language sentence can capture the inter...
research
04/19/2017

Dependency resolution and semantic mining using Tree Adjoining Grammars for Tamil Language

Tree adjoining grammars (TAGs) provide an ample tool to capture syntax o...
research
03/31/2020

Inherent Dependency Displacement Bias of Transition-Based Algorithms

A wide variety of transition-based algorithms are currently used for dep...

Please sign up or login with your details

Forgot password? Click here to reset