<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tackstrom-etal-2015-efficient">
    <titleInfo>
        <title>Efficient Inference and Structured Learning for Semantic Role Labeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Oscar</namePart>
        <namePart type="family">Täckström</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kuzman</namePart>
        <namePart type="family">Ganchev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dipanjan</namePart>
        <namePart type="family">Das</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2015</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>We present a dynamic programming algorithm for efficient constrained inference in semantic role labeling. The algorithm tractably captures a majority of the structural constraints examined by prior work in this area, which has resorted to either approximate methods or off-the-shelf integer linear programming solvers. In addition, it allows training a globally-normalized log-linear model with respect to constrained conditional likelihood. We show that the dynamic program is several times faster than an off-the-shelf integer linear programming solver, while reaching the same solution. Furthermore, we show that our structured model results in significant improvements over its local counterpart, achieving state-of-the-art results on both PropBank- and FrameNet-annotated corpora.</abstract>
    <identifier type="citekey">tackstrom-etal-2015-efficient</identifier>
    <identifier type="doi">10.1162/tacl_a_00120</identifier>
    <location>
        <url>https://aclanthology.org/Q15-1003</url>
    </location>
    <part>
        <date>2015</date>
        <detail type="volume"><number>3</number></detail>
        <extent unit="page">
            <start>29</start>
            <end>41</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Efficient Inference and Structured Learning for Semantic Role Labeling
%A Täckström, Oscar
%A Ganchev, Kuzman
%A Das, Dipanjan
%J Transactions of the Association for Computational Linguistics
%D 2015
%V 3
%I MIT Press
%C Cambridge, MA
%F tackstrom-etal-2015-efficient
%X We present a dynamic programming algorithm for efficient constrained inference in semantic role labeling. The algorithm tractably captures a majority of the structural constraints examined by prior work in this area, which has resorted to either approximate methods or off-the-shelf integer linear programming solvers. In addition, it allows training a globally-normalized log-linear model with respect to constrained conditional likelihood. We show that the dynamic program is several times faster than an off-the-shelf integer linear programming solver, while reaching the same solution. Furthermore, we show that our structured model results in significant improvements over its local counterpart, achieving state-of-the-art results on both PropBank- and FrameNet-annotated corpora.
%R 10.1162/tacl_a_00120
%U https://aclanthology.org/Q15-1003
%U https://doi.org/10.1162/tacl_a_00120
%P 29-41

Markdown (Informal)

[Efficient Inference and Structured Learning for Semantic Role Labeling](https://aclanthology.org/Q15-1003) (Täckström et al., TACL 2015)

• Efficient Inference and Structured Learning for Semantic Role Labeling (Täckström et al., TACL 2015)

ACL

• Oscar Täckström, Kuzman Ganchev, and Dipanjan Das. 2015. Efficient Inference and Structured Learning for Semantic Role Labeling. Transactions of the Association for Computational Linguistics, 3:29–41.