<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2019-generative">
    <titleInfo>
        <title>A Generative Model for Punctuation in Dependency Trees</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiang</namePart>
        <namePart type="given">Lisa</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dingquan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jason</namePart>
        <namePart type="family">Eisner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019</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>Treebanks traditionally treat punctuation marks as ordinary words, but linguists have suggested that a tree’s “true” punctuation marks are not observed (Nunberg, 1990). These latent “underlying” marks serve to delimit or separate constituents in the syntax tree. When the tree’s yield is rendered as a written sentence, a string rewriting mechanism transduces the underlying marks into “surface” marks, which are part of the observed (surface) string but should not be regarded as part of the tree. We formalize this idea in a generative model of punctuation that admits efficient dynamic programming. We train it without observing the underlying marks, by locally maximizing the incomplete data likelihood (similarly to the EM algorithm). When we use the trained model to reconstruct the tree’s underlying punctuation, the results appear plausible across 5 languages, and in particular are consistent with Nunberg’s analysis of English. We show that our generative model can be used to beat baselines on punctuation restoration. Also, our reconstruction of a sentence’s underlying punctuation lets us appropriately render the surface punctuation (via our trained underlying-to-surface mechanism) when we syntactically transform the sentence.</abstract>
    <identifier type="citekey">li-etal-2019-generative</identifier>
    <identifier type="doi">10.1162/tacl_a_00273</identifier>
    <location>
        <url>https://aclanthology.org/Q19-1023</url>
    </location>
    <part>
        <date>2019</date>
        <detail type="volume"><number>7</number></detail>
        <extent unit="page">
            <start>357</start>
            <end>373</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T A Generative Model for Punctuation in Dependency Trees
%A Li, Xiang Lisa
%A Wang, Dingquan
%A Eisner, Jason
%J Transactions of the Association for Computational Linguistics
%D 2019
%V 7
%I MIT Press
%C Cambridge, MA
%F li-etal-2019-generative
%X Treebanks traditionally treat punctuation marks as ordinary words, but linguists have suggested that a tree’s “true” punctuation marks are not observed (Nunberg, 1990). These latent “underlying” marks serve to delimit or separate constituents in the syntax tree. When the tree’s yield is rendered as a written sentence, a string rewriting mechanism transduces the underlying marks into “surface” marks, which are part of the observed (surface) string but should not be regarded as part of the tree. We formalize this idea in a generative model of punctuation that admits efficient dynamic programming. We train it without observing the underlying marks, by locally maximizing the incomplete data likelihood (similarly to the EM algorithm). When we use the trained model to reconstruct the tree’s underlying punctuation, the results appear plausible across 5 languages, and in particular are consistent with Nunberg’s analysis of English. We show that our generative model can be used to beat baselines on punctuation restoration. Also, our reconstruction of a sentence’s underlying punctuation lets us appropriately render the surface punctuation (via our trained underlying-to-surface mechanism) when we syntactically transform the sentence.
%R 10.1162/tacl_a_00273
%U https://aclanthology.org/Q19-1023
%U https://doi.org/10.1162/tacl_a_00273
%P 357-373

Markdown (Informal)

[A Generative Model for Punctuation in Dependency Trees](https://aclanthology.org/Q19-1023) (Li et al., TACL 2019)

• A Generative Model for Punctuation in Dependency Trees (Li et al., TACL 2019)

ACL

• Xiang Lisa Li, Dingquan Wang, and Jason Eisner. 2019. A Generative Model for Punctuation in Dependency Trees. Transactions of the Association for Computational Linguistics, 7:357–373.