<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suresh-etal-2021-approximating">
    <titleInfo>
        <title>Approximating Probabilistic Models as Weighted Finite Automata</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ananda</namePart>
        <namePart type="given">Theertha</namePart>
        <namePart type="family">Suresh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Brian</namePart>
        <namePart type="family">Roark</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Riley</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vlad</namePart>
        <namePart type="family">Schogol</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>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>Weighted finite automata (WFAs) are often used to represent probabilistic models, such as n-gram language models, because among other things, they are efficient for recognition tasks in time and space. The probabilistic source to be represented as a WFA, however, may come in many forms. Given a generic probabilistic model over sequences, we propose an algorithm to approximate it as a WFA such that the Kullback-Leibler divergence between the source model and the WFA target model is minimized. The proposed algorithm involves a counting step and a difference of convex optimization step, both of which can be performed efficiently. We demonstrate the usefulness of our approach on various tasks, including distilling n-gram models from neural models, building compact language models, and building open-vocabulary character models. The algorithms used for these experiments are available in an open-source software library.</abstract>
    <identifier type="citekey">suresh-etal-2021-approximating</identifier>
    <identifier type="doi">10.1162/coli_a_00401</identifier>
    <location>
        <url>https://aclanthology.org/2021.cl-2.9/</url>
    </location>
    <part>
        <date>2021-06</date>
        <detail type="volume"><number>47</number></detail>
        <detail type="issue"><number>2</number></detail>
        <extent unit="page">
            <start>221</start>
            <end>254</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Approximating Probabilistic Models as Weighted Finite Automata
%A Suresh, Ananda Theertha
%A Roark, Brian
%A Riley, Michael
%A Schogol, Vlad
%J Computational Linguistics
%D 2021
%8 June
%V 47
%N 2
%I MIT Press
%C Cambridge, MA
%F suresh-etal-2021-approximating
%X Weighted finite automata (WFAs) are often used to represent probabilistic models, such as n-gram language models, because among other things, they are efficient for recognition tasks in time and space. The probabilistic source to be represented as a WFA, however, may come in many forms. Given a generic probabilistic model over sequences, we propose an algorithm to approximate it as a WFA such that the Kullback-Leibler divergence between the source model and the WFA target model is minimized. The proposed algorithm involves a counting step and a difference of convex optimization step, both of which can be performed efficiently. We demonstrate the usefulness of our approach on various tasks, including distilling n-gram models from neural models, building compact language models, and building open-vocabulary character models. The algorithms used for these experiments are available in an open-source software library.
%R 10.1162/coli_a_00401
%U https://aclanthology.org/2021.cl-2.9/
%U https://doi.org/10.1162/coli_a_00401
%P 221-254

Markdown (Informal)

[Approximating Probabilistic Models as Weighted Finite Automata](https://aclanthology.org/2021.cl-2.9/) (Suresh et al., CL 2021)

• Approximating Probabilistic Models as Weighted Finite Automata (Suresh et al., CL 2021)

ACL

• Ananda Theertha Suresh, Brian Roark, Michael Riley, and Vlad Schogol. 2021. Approximating Probabilistic Models as Weighted Finite Automata. Computational Linguistics, 47(2):221–254.