@inproceedings{keith-etal-2018-monte,
title = "{M}onte {C}arlo Syntax Marginals for Exploring and Using Dependency Parses",
author = "Keith, Katherine and
Blodgett, Su Lin and
O{'}Connor, Brendan",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1084",
doi = "10.18653/v1/N18-1084",
pages = "917--928",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keith-etal-2018-monte">
<titleInfo>
<title>Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Keith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brendan</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">keith-etal-2018-monte</identifier>
<identifier type="doi">10.18653/v1/N18-1084</identifier>
<location>
<url>https://aclanthology.org/N18-1084</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>917</start>
<end>928</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses
%A Keith, Katherine
%A Blodgett, Su Lin
%A O’Connor, Brendan
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F keith-etal-2018-monte
%X 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.
%R 10.18653/v1/N18-1084
%U https://aclanthology.org/N18-1084
%U https://doi.org/10.18653/v1/N18-1084
%P 917-928
Markdown (Informal)
[Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses](https://aclanthology.org/N18-1084) (Keith et al., NAACL 2018)
ACL
- Katherine Keith, Su Lin Blodgett, and Brendan O’Connor. 2018. Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 917–928, New Orleans, Louisiana. Association for Computational Linguistics.