@article{effland-collins-2023-improving,
title = "Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization",
author = "Effland, Thomas and
Collins, Michael",
journal = "Transactions of the Association for Computational Linguistics",
volume = "11",
year = "2023",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2023.tacl-1.8",
doi = "10.1162/tacl_a_00537",
pages = "122--138",
abstract = "We present Expected Statistic Regulariza tion (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi- supervised learning on low-resource datasets. We study ESR in the context of cross-lingual transfer for syntactic analysis (POS tagging and labeled dependency parsing) and present several classes of low-order statistic functions that bear on model behavior. Experimentally, we evaluate the proposed statistics with ESR for unsupervised transfer on 5 diverse target languages and show that all statistics, when estimated accurately, yield improvements to both POS and LAS, with the best statistic improving POS by +7.0 and LAS by +8.5 on average. We also present semi-supervised transfer and learning curve experiments that show ESR provides significant gains over strong cross-lingual-transfer-plus-fine-tuning baselines for modest amounts of label data. These results indicate that ESR is a promising and complementary approach to model-transfer approaches for cross-lingual parsing.1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="effland-collins-2023-improving">
<titleInfo>
<title>Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Effland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Collins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023</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>We present Expected Statistic Regulariza tion (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi- supervised learning on low-resource datasets. We study ESR in the context of cross-lingual transfer for syntactic analysis (POS tagging and labeled dependency parsing) and present several classes of low-order statistic functions that bear on model behavior. Experimentally, we evaluate the proposed statistics with ESR for unsupervised transfer on 5 diverse target languages and show that all statistics, when estimated accurately, yield improvements to both POS and LAS, with the best statistic improving POS by +7.0 and LAS by +8.5 on average. We also present semi-supervised transfer and learning curve experiments that show ESR provides significant gains over strong cross-lingual-transfer-plus-fine-tuning baselines for modest amounts of label data. These results indicate that ESR is a promising and complementary approach to model-transfer approaches for cross-lingual parsing.1</abstract>
<identifier type="citekey">effland-collins-2023-improving</identifier>
<identifier type="doi">10.1162/tacl_a_00537</identifier>
<location>
<url>https://aclanthology.org/2023.tacl-1.8</url>
</location>
<part>
<date>2023</date>
<detail type="volume"><number>11</number></detail>
<extent unit="page">
<start>122</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization
%A Effland, Thomas
%A Collins, Michael
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F effland-collins-2023-improving
%X We present Expected Statistic Regulariza tion (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi- supervised learning on low-resource datasets. We study ESR in the context of cross-lingual transfer for syntactic analysis (POS tagging and labeled dependency parsing) and present several classes of low-order statistic functions that bear on model behavior. Experimentally, we evaluate the proposed statistics with ESR for unsupervised transfer on 5 diverse target languages and show that all statistics, when estimated accurately, yield improvements to both POS and LAS, with the best statistic improving POS by +7.0 and LAS by +8.5 on average. We also present semi-supervised transfer and learning curve experiments that show ESR provides significant gains over strong cross-lingual-transfer-plus-fine-tuning baselines for modest amounts of label data. These results indicate that ESR is a promising and complementary approach to model-transfer approaches for cross-lingual parsing.1
%R 10.1162/tacl_a_00537
%U https://aclanthology.org/2023.tacl-1.8
%U https://doi.org/10.1162/tacl_a_00537
%P 122-138
Markdown (Informal)
[Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization](https://aclanthology.org/2023.tacl-1.8) (Effland & Collins, TACL 2023)
ACL