<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vieira-eisner-2017-learning">
    <titleInfo>
        <title>Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tim</namePart>
        <namePart type="family">Vieira</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jason</namePart>
        <namePart type="family">Eisner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017</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>Pruning hypotheses during dynamic programming is commonly used to speed up inference in settings such as parsing. Unlike prior work, we train a pruning policy under an objective that measures end-to-end performance: we search for a fast and accurate policy. This poses a difficult machine learning problem, which we tackle with the lols algorithm. lols training must continually compute the effects of changing pruning decisions: we show how to make this efficient in the constituency parsing setting, via dynamic programming and change propagation algorithms. We find that optimizing end-to-end performance in this way leads to a better Pareto frontier—i.e., parsers which are more accurate for a given runtime.</abstract>
    <identifier type="citekey">vieira-eisner-2017-learning</identifier>
    <identifier type="doi">10.1162/tacl_a_00060</identifier>
    <location>
        <url>https://aclanthology.org/Q17-1019</url>
    </location>
    <part>
        <date>2017</date>
        <detail type="volume"><number>5</number></detail>
        <extent unit="page">
            <start>263</start>
            <end>278</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing
%A Vieira, Tim
%A Eisner, Jason
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F vieira-eisner-2017-learning
%X Pruning hypotheses during dynamic programming is commonly used to speed up inference in settings such as parsing. Unlike prior work, we train a pruning policy under an objective that measures end-to-end performance: we search for a fast and accurate policy. This poses a difficult machine learning problem, which we tackle with the lols algorithm. lols training must continually compute the effects of changing pruning decisions: we show how to make this efficient in the constituency parsing setting, via dynamic programming and change propagation algorithms. We find that optimizing end-to-end performance in this way leads to a better Pareto frontier—i.e., parsers which are more accurate for a given runtime.
%R 10.1162/tacl_a_00060
%U https://aclanthology.org/Q17-1019
%U https://doi.org/10.1162/tacl_a_00060
%P 263-278

Markdown (Informal)

[Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing](https://aclanthology.org/Q17-1019) (Vieira & Eisner, TACL 2017)

• Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing (Vieira & Eisner, TACL 2017)

ACL

• Tim Vieira and Jason Eisner. 2017. Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing. Transactions of the Association for Computational Linguistics, 5:263–278.