@article{jin-etal-2018-unsupervised,
title = "Unsupervised Grammar Induction with Depth-bounded {PCFG}",
author = "Jin, Lifeng and
Doshi-Velez, Finale and
Miller, Timothy and
Schuler, William and
Schwartz, Lane",
editor = "Lee, Lillian and
Johnson, Mark and
Toutanova, Kristina and
Roark, Brian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "6",
year = "2018",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q18-1016",
doi = "10.1162/tacl_a_00016",
pages = "211--224",
abstract = "There has been recent interest in applying cognitively- or empirically-motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchical sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech and newswire text exceed or are competitive with those of other models when evaluated on parse accuracy. Moreover, grammars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2018-unsupervised">
<titleInfo>
<title>Unsupervised Grammar Induction with Depth-bounded PCFG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Finale</namePart>
<namePart type="family">Doshi-Velez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Schuler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</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>There has been recent interest in applying cognitively- or empirically-motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchical sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech and newswire text exceed or are competitive with those of other models when evaluated on parse accuracy. Moreover, grammars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.</abstract>
<identifier type="citekey">jin-etal-2018-unsupervised</identifier>
<identifier type="doi">10.1162/tacl_a_00016</identifier>
<location>
<url>https://aclanthology.org/Q18-1016</url>
</location>
<part>
<date>2018</date>
<detail type="volume"><number>6</number></detail>
<extent unit="page">
<start>211</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Unsupervised Grammar Induction with Depth-bounded PCFG
%A Jin, Lifeng
%A Doshi-Velez, Finale
%A Miller, Timothy
%A Schuler, William
%A Schwartz, Lane
%J Transactions of the Association for Computational Linguistics
%D 2018
%V 6
%I MIT Press
%C Cambridge, MA
%F jin-etal-2018-unsupervised
%X There has been recent interest in applying cognitively- or empirically-motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchical sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech and newswire text exceed or are competitive with those of other models when evaluated on parse accuracy. Moreover, grammars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.
%R 10.1162/tacl_a_00016
%U https://aclanthology.org/Q18-1016
%U https://doi.org/10.1162/tacl_a_00016
%P 211-224
Markdown (Informal)
[Unsupervised Grammar Induction with Depth-bounded PCFG](https://aclanthology.org/Q18-1016) (Jin et al., TACL 2018)
ACL