<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berant-liang-2015-imitation">
    <titleInfo>
        <title>Imitation Learning of Agenda-based Semantic Parsers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Berant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Percy</namePart>
        <namePart type="family">Liang</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>Semantic parsers conventionally construct logical forms bottom-up in a fixed order, resulting in the generation of many extraneous partial logical forms. In this paper, we combine ideas from imitation learning and agenda-based parsing to train a semantic parser that searches partial logical forms in a more strategic order. Empirically, our parser reduces the number of constructed partial logical forms by an order of magnitude, and obtains a 6x-9x speedup over fixed-order parsing, while maintaining comparable accuracy.</abstract>
    <identifier type="citekey">berant-liang-2015-imitation</identifier>
    <identifier type="doi">10.1162/tacl_a_00157</identifier>
    <location>
        <url>https://aclanthology.org/Q15-1039</url>
    </location>
    <part>
        <date>2015</date>
        <detail type="volume"><number>3</number></detail>
        <extent unit="page">
            <start>545</start>
            <end>558</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Imitation Learning of Agenda-based Semantic Parsers
%A Berant, Jonathan
%A Liang, Percy
%J Transactions of the Association for Computational Linguistics
%D 2015
%V 3
%I MIT Press
%C Cambridge, MA
%F berant-liang-2015-imitation
%X Semantic parsers conventionally construct logical forms bottom-up in a fixed order, resulting in the generation of many extraneous partial logical forms. In this paper, we combine ideas from imitation learning and agenda-based parsing to train a semantic parser that searches partial logical forms in a more strategic order. Empirically, our parser reduces the number of constructed partial logical forms by an order of magnitude, and obtains a 6x-9x speedup over fixed-order parsing, while maintaining comparable accuracy.
%R 10.1162/tacl_a_00157
%U https://aclanthology.org/Q15-1039
%U https://doi.org/10.1162/tacl_a_00157
%P 545-558

Markdown (Informal)

[Imitation Learning of Agenda-based Semantic Parsers](https://aclanthology.org/Q15-1039) (Berant & Liang, TACL 2015)

• Imitation Learning of Agenda-based Semantic Parsers (Berant & Liang, TACL 2015)

ACL

• Jonathan Berant and Percy Liang. 2015. Imitation Learning of Agenda-based Semantic Parsers. Transactions of the Association for Computational Linguistics, 3:545–558.