@inproceedings{jin-etal-2021-character-based,
title = "Character-based {PCFG} Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages",
author = "Jin, Lifeng and
Oh, Byung-Doh and
Schuler, William",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.371",
doi = "10.18653/v1/2021.findings-emnlp.371",
pages = "4367--4378",
abstract = "Unsupervised PCFG induction models, which build syntactic structures from raw text, can be used to evaluate the extent to which syntactic knowledge can be acquired from distributional information alone. However, many state-of-the-art PCFG induction models are word-based, meaning that they cannot directly inspect functional affixes, which may provide crucial information for syntactic acquisition in child learners. This work first introduces a neural PCFG induction model that allows a clean ablation of the influence of subword information in grammar induction. Experiments on child-directed speech demonstrate first that the incorporation of subword information results in more accurate grammars with categories that word-based induction models have difficulty finding, and second that this effect is amplified in morphologically richer languages that rely on functional affixes to express grammatical relations. A subsequent evaluation on multilingual treebanks shows that the model with subword information achieves state-of-the-art results on many languages, further supporting a distributional model of syntactic acquisition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2021-character-based">
<titleInfo>
<title>Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages</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">Byung-Doh</namePart>
<namePart type="family">Oh</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>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unsupervised PCFG induction models, which build syntactic structures from raw text, can be used to evaluate the extent to which syntactic knowledge can be acquired from distributional information alone. However, many state-of-the-art PCFG induction models are word-based, meaning that they cannot directly inspect functional affixes, which may provide crucial information for syntactic acquisition in child learners. This work first introduces a neural PCFG induction model that allows a clean ablation of the influence of subword information in grammar induction. Experiments on child-directed speech demonstrate first that the incorporation of subword information results in more accurate grammars with categories that word-based induction models have difficulty finding, and second that this effect is amplified in morphologically richer languages that rely on functional affixes to express grammatical relations. A subsequent evaluation on multilingual treebanks shows that the model with subword information achieves state-of-the-art results on many languages, further supporting a distributional model of syntactic acquisition.</abstract>
<identifier type="citekey">jin-etal-2021-character-based</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.371</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.371</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4367</start>
<end>4378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages
%A Jin, Lifeng
%A Oh, Byung-Doh
%A Schuler, William
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F jin-etal-2021-character-based
%X Unsupervised PCFG induction models, which build syntactic structures from raw text, can be used to evaluate the extent to which syntactic knowledge can be acquired from distributional information alone. However, many state-of-the-art PCFG induction models are word-based, meaning that they cannot directly inspect functional affixes, which may provide crucial information for syntactic acquisition in child learners. This work first introduces a neural PCFG induction model that allows a clean ablation of the influence of subword information in grammar induction. Experiments on child-directed speech demonstrate first that the incorporation of subword information results in more accurate grammars with categories that word-based induction models have difficulty finding, and second that this effect is amplified in morphologically richer languages that rely on functional affixes to express grammatical relations. A subsequent evaluation on multilingual treebanks shows that the model with subword information achieves state-of-the-art results on many languages, further supporting a distributional model of syntactic acquisition.
%R 10.18653/v1/2021.findings-emnlp.371
%U https://aclanthology.org/2021.findings-emnlp.371
%U https://doi.org/10.18653/v1/2021.findings-emnlp.371
%P 4367-4378
Markdown (Informal)
[Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages](https://aclanthology.org/2021.findings-emnlp.371) (Jin et al., Findings 2021)
ACL