@article{vaswani-sagae-2016-efficient,
title = "Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States",
author = "Vaswani, Ashish and
Sagae, Kenji",
editor = "Lee, Lillian and
Johnson, Mark and
Toutanova, Kristina",
journal = "Transactions of the Association for Computational Linguistics",
volume = "4",
year = "2016",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q16-1014",
doi = "10.1162/tacl_a_00092",
pages = "183--196",
abstract = "Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art. In this paper, we propose a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models. This is accomplished with the introduction of error states in local training, which add information about incorrect derivation paths typically left out completely in locally-trained models. Using neural networks for our local classifiers, our approach achieves 93.61{\%} accuracy for transition-based dependency parsing in English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vaswani-sagae-2016-efficient">
<titleInfo>
<title>Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Vaswani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Sagae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art. In this paper, we propose a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models. This is accomplished with the introduction of error states in local training, which add information about incorrect derivation paths typically left out completely in locally-trained models. Using neural networks for our local classifiers, our approach achieves 93.61% accuracy for transition-based dependency parsing in English.</abstract>
<identifier type="citekey">vaswani-sagae-2016-efficient</identifier>
<identifier type="doi">10.1162/tacl_a_00092</identifier>
<location>
<url>https://aclanthology.org/Q16-1014</url>
</location>
<part>
<date>2016</date>
<detail type="volume"><number>4</number></detail>
<extent unit="page">
<start>183</start>
<end>196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States
%A Vaswani, Ashish
%A Sagae, Kenji
%J Transactions of the Association for Computational Linguistics
%D 2016
%V 4
%I MIT Press
%C Cambridge, MA
%F vaswani-sagae-2016-efficient
%X Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art. In this paper, we propose a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models. This is accomplished with the introduction of error states in local training, which add information about incorrect derivation paths typically left out completely in locally-trained models. Using neural networks for our local classifiers, our approach achieves 93.61% accuracy for transition-based dependency parsing in English.
%R 10.1162/tacl_a_00092
%U https://aclanthology.org/Q16-1014
%U https://doi.org/10.1162/tacl_a_00092
%P 183-196
Markdown (Informal)
[Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States](https://aclanthology.org/Q16-1014) (Vaswani & Sagae, TACL 2016)
ACL