<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matthews-etal-2019-comparing">
    <titleInfo>
        <title>Comparing Top-Down and Bottom-Up Neural Generative Dependency Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Austin</namePart>
        <namePart type="family">Matthews</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chris</namePart>
        <namePart type="family">Dyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recurrent neural network grammars generate sentences using phrase-structure syntax and perform very well on both parsing and language modeling. To explore whether generative dependency models are similarly effective, we propose two new generative models of dependency syntax. Both models use recurrent neural nets to avoid making explicit independence assumptions, but they differ in the order used to construct the trees: one builds the tree bottom-up and the other top-down, which profoundly changes the estimation problem faced by the learner. We evaluate the two models on three typologically different languages: English, Arabic, and Japanese. While both generative models improve parsing performance over a discriminative baseline, they are significantly less effective than non-syntactic LSTM language models. Surprisingly, little difference between the construction orders is observed for either parsing or language modeling.</abstract>
    <identifier type="citekey">matthews-etal-2019-comparing</identifier>
    <identifier type="doi">10.18653/v1/K19-1022</identifier>
    <location>
        <url>https://aclanthology.org/K19-1022</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>227</start>
            <end>237</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comparing Top-Down and Bottom-Up Neural Generative Dependency Models
%A Matthews, Austin
%A Neubig, Graham
%A Dyer, Chris
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F matthews-etal-2019-comparing
%X Recurrent neural network grammars generate sentences using phrase-structure syntax and perform very well on both parsing and language modeling. To explore whether generative dependency models are similarly effective, we propose two new generative models of dependency syntax. Both models use recurrent neural nets to avoid making explicit independence assumptions, but they differ in the order used to construct the trees: one builds the tree bottom-up and the other top-down, which profoundly changes the estimation problem faced by the learner. We evaluate the two models on three typologically different languages: English, Arabic, and Japanese. While both generative models improve parsing performance over a discriminative baseline, they are significantly less effective than non-syntactic LSTM language models. Surprisingly, little difference between the construction orders is observed for either parsing or language modeling.
%R 10.18653/v1/K19-1022
%U https://aclanthology.org/K19-1022
%U https://doi.org/10.18653/v1/K19-1022
%P 227-237

Markdown (Informal)

[Comparing Top-Down and Bottom-Up Neural Generative Dependency Models](https://aclanthology.org/K19-1022) (Matthews et al., CoNLL 2019)

• Comparing Top-Down and Bottom-Up Neural Generative Dependency Models (Matthews et al., CoNLL 2019)

ACL

• Austin Matthews, Graham Neubig, and Chris Dyer. 2019. Comparing Top-Down and Bottom-Up Neural Generative Dependency Models. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 227–237, Hong Kong, China. Association for Computational Linguistics.