<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buckman-neubig-2018-neural">
    <titleInfo>
        <title>Neural Lattice Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jacob</namePart>
        <namePart type="family">Buckman</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>
    <originInfo>
        <dateIssued>2018</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>In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of possible paths through a sentence and marginalize across this lattice to calculate sequence probabilities or optimize parameters. This approach allows us to seamlessly incorporate linguistic intuitions — including polysemy and the existence of multiword lexical items — into our language model. Experiments on multiple language modeling tasks show that English neural lattice language models that utilize polysemous embeddings are able to improve perplexity by 9.95% relative to a word-level baseline, and that a Chinese model that handles multi-character tokens is able to improve perplexity by 20.94% relative to a character-level baseline.</abstract>
    <identifier type="citekey">buckman-neubig-2018-neural</identifier>
    <identifier type="doi">10.1162/tacl_a_00036</identifier>
    <location>
        <url>https://aclanthology.org/Q18-1036</url>
    </location>
    <part>
        <date>2018</date>
        <detail type="volume"><number>6</number></detail>
        <extent unit="page">
            <start>529</start>
            <end>541</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Neural Lattice Language Models
%A Buckman, Jacob
%A Neubig, Graham
%J Transactions of the Association for Computational Linguistics
%D 2018
%V 6
%I MIT Press
%C Cambridge, MA
%F buckman-neubig-2018-neural
%X In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of possible paths through a sentence and marginalize across this lattice to calculate sequence probabilities or optimize parameters. This approach allows us to seamlessly incorporate linguistic intuitions — including polysemy and the existence of multiword lexical items — into our language model. Experiments on multiple language modeling tasks show that English neural lattice language models that utilize polysemous embeddings are able to improve perplexity by 9.95% relative to a word-level baseline, and that a Chinese model that handles multi-character tokens is able to improve perplexity by 20.94% relative to a character-level baseline.
%R 10.1162/tacl_a_00036
%U https://aclanthology.org/Q18-1036
%U https://doi.org/10.1162/tacl_a_00036
%P 529-541

Markdown (Informal)

[Neural Lattice Language Models](https://aclanthology.org/Q18-1036) (Buckman & Neubig, TACL 2018)

• Neural Lattice Language Models (Buckman & Neubig, TACL 2018)

ACL

• Jacob Buckman and Graham Neubig. 2018. Neural Lattice Language Models. Transactions of the Association for Computational Linguistics, 6:529–541.