<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-zhang-2017-shift">
    <titleInfo>
        <title>Shift-Reduce Constituent Parsing with Neural Lookahead Features</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiangming</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Zhang</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>Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which consists of a sequence of non-local constituents. On the other hand, during incremental parsing, constituent information on the right hand side of the current word is not utilized, which is a relative weakness of shift-reduce parsing. To address this limitation, we leverage a fast neural model to extract lookahead features. In particular, we build a bidirectional LSTM model, which leverages full sentence information to predict the hierarchy of constituents that each word starts and ends. The results are then passed to a strong transition-based constituent parser as lookahead features. The resulting parser gives 1.3% absolute improvement in WSJ and 2.3% in CTB compared to the baseline, giving the highest reported accuracies for fully-supervised parsing.</abstract>
    <identifier type="citekey">liu-zhang-2017-shift</identifier>
    <identifier type="doi">10.1162/tacl_a_00045</identifier>
    <location>
        <url>https://aclanthology.org/Q17-1004</url>
    </location>
    <part>
        <date>2017</date>
        <detail type="volume"><number>5</number></detail>
        <extent unit="page">
            <start>45</start>
            <end>58</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Shift-Reduce Constituent Parsing with Neural Lookahead Features
%A Liu, Jiangming
%A Zhang, Yue
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F liu-zhang-2017-shift
%X Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which consists of a sequence of non-local constituents. On the other hand, during incremental parsing, constituent information on the right hand side of the current word is not utilized, which is a relative weakness of shift-reduce parsing. To address this limitation, we leverage a fast neural model to extract lookahead features. In particular, we build a bidirectional LSTM model, which leverages full sentence information to predict the hierarchy of constituents that each word starts and ends. The results are then passed to a strong transition-based constituent parser as lookahead features. The resulting parser gives 1.3% absolute improvement in WSJ and 2.3% in CTB compared to the baseline, giving the highest reported accuracies for fully-supervised parsing.
%R 10.1162/tacl_a_00045
%U https://aclanthology.org/Q17-1004
%U https://doi.org/10.1162/tacl_a_00045
%P 45-58

Markdown (Informal)

[Shift-Reduce Constituent Parsing with Neural Lookahead Features](https://aclanthology.org/Q17-1004) (Liu & Zhang, TACL 2017)

• Shift-Reduce Constituent Parsing with Neural Lookahead Features (Liu & Zhang, TACL 2017)

ACL

• Jiangming Liu and Yue Zhang. 2017. Shift-Reduce Constituent Parsing with Neural Lookahead Features. Transactions of the Association for Computational Linguistics, 5:45–58.