<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fried-etal-2019-cross">
    <titleInfo>
        <title>Cross-Domain Generalization of Neural Constituency Parsers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Fried</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nikita</namePart>
        <namePart type="family">Kitaev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dan</namePart>
        <namePart type="family">Klein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural parsers obtain state-of-the-art results on benchmark treebanks for constituency parsing—but to what degree do they generalize to other domains? We present three results about the generalization of neural parsers in a zero-shot setting: training on trees from one corpus and evaluating on out-of-domain corpora. First, neural and non-neural parsers generalize comparably to new domains. Second, incorporating pre-trained encoder representations into neural parsers substantially improves their performance across all domains, but does not give a larger relative improvement for out-of-domain treebanks. Finally, despite the rich input representations they learn, neural parsers still benefit from structured output prediction of output trees, yielding higher exact match accuracy and stronger generalization both to larger text spans and to out-of-domain corpora. We analyze generalization on English and Chinese corpora, and in the process obtain state-of-the-art parsing results for the Brown, Genia, and English Web treebanks.</abstract>
    <identifier type="citekey">fried-etal-2019-cross</identifier>
    <identifier type="doi">10.18653/v1/P19-1031</identifier>
    <location>
        <url>https://aclanthology.org/P19-1031/</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>323</start>
            <end>330</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-Domain Generalization of Neural Constituency Parsers
%A Fried, Daniel
%A Kitaev, Nikita
%A Klein, Dan
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F fried-etal-2019-cross
%X Neural parsers obtain state-of-the-art results on benchmark treebanks for constituency parsing—but to what degree do they generalize to other domains? We present three results about the generalization of neural parsers in a zero-shot setting: training on trees from one corpus and evaluating on out-of-domain corpora. First, neural and non-neural parsers generalize comparably to new domains. Second, incorporating pre-trained encoder representations into neural parsers substantially improves their performance across all domains, but does not give a larger relative improvement for out-of-domain treebanks. Finally, despite the rich input representations they learn, neural parsers still benefit from structured output prediction of output trees, yielding higher exact match accuracy and stronger generalization both to larger text spans and to out-of-domain corpora. We analyze generalization on English and Chinese corpora, and in the process obtain state-of-the-art parsing results for the Brown, Genia, and English Web treebanks.
%R 10.18653/v1/P19-1031
%U https://aclanthology.org/P19-1031/
%U https://doi.org/10.18653/v1/P19-1031
%P 323-330

Markdown (Informal)

[Cross-Domain Generalization of Neural Constituency Parsers](https://aclanthology.org/P19-1031/) (Fried et al., ACL 2019)

• Cross-Domain Generalization of Neural Constituency Parsers (Fried et al., ACL 2019)

ACL

• Daniel Fried, Nikita Kitaev, and Dan Klein. 2019. Cross-Domain Generalization of Neural Constituency Parsers. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 323–330, Florence, Italy. Association for Computational Linguistics.