<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maveli-cohen-2022-co">
    <titleInfo>
        <title>Co-training an Unsupervised Constituency Parser with Weak Supervision</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nickil</namePart>
        <namePart type="family">Maveli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shay</namePart>
        <namePart type="family">Cohen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, an inside classifier that acts on a span, and an outside classifier that acts on everything outside of a given span. Through self-training and co-training with the two classifiers, we show that the interplay between them helps improve the accuracy of both, and as a result, effectively parse. A seed bootstrapping technique prepares the data to train these classifiers. Our analyses further validate that such an approach in conjunction with weak supervision using prior branching knowledge of a known language (left/right-branching) and minimal heuristics injects strong inductive bias into the parser, achieving 63.1 F₁ on the English (PTB) test set. In addition, we show the effectiveness of our architecture by evaluating on treebanks for Chinese (CTB) and Japanese (KTB) and achieve new state-of-the-art results.</abstract>
    <identifier type="citekey">maveli-cohen-2022-co</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.101</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.101</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>1274</start>
            <end>1291</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Co-training an Unsupervised Constituency Parser with Weak Supervision
%A Maveli, Nickil
%A Cohen, Shay
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F maveli-cohen-2022-co
%X We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, an inside classifier that acts on a span, and an outside classifier that acts on everything outside of a given span. Through self-training and co-training with the two classifiers, we show that the interplay between them helps improve the accuracy of both, and as a result, effectively parse. A seed bootstrapping technique prepares the data to train these classifiers. Our analyses further validate that such an approach in conjunction with weak supervision using prior branching knowledge of a known language (left/right-branching) and minimal heuristics injects strong inductive bias into the parser, achieving 63.1 F₁ on the English (PTB) test set. In addition, we show the effectiveness of our architecture by evaluating on treebanks for Chinese (CTB) and Japanese (KTB) and achieve new state-of-the-art results.
%R 10.18653/v1/2022.findings-acl.101
%U https://aclanthology.org/2022.findings-acl.101
%U https://doi.org/10.18653/v1/2022.findings-acl.101
%P 1274-1291

Markdown (Informal)

[Co-training an Unsupervised Constituency Parser with Weak Supervision](https://aclanthology.org/2022.findings-acl.101) (Maveli & Cohen, Findings 2022)

• Co-training an Unsupervised Constituency Parser with Weak Supervision (Maveli & Cohen, Findings 2022)

ACL

• Nickil Maveli and Shay Cohen. 2022. Co-training an Unsupervised Constituency Parser with Weak Supervision. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1274–1291, Dublin, Ireland. Association for Computational Linguistics.