<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="indurkhya-2021-using">
    <titleInfo>
        <title>Using Collaborative Filtering to Model Argument Selection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sagar</namePart>
        <namePart type="family">Indurkhya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-sep</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
        </titleInfo>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Held Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study evaluates whether model-based Collaborative Filtering (CF) algorithms, which have been extensively studied and widely used to build recommender systems, can be used to predict which common nouns a predicate can take as its complement. We find that, when trained on verb-noun co-occurrence data drawn from the Corpus of Contemporary American-English (COCA), two popular model-based CF algorithms, Singular Value Decomposition and Non-negative Matrix Factorization, perform well on this task, each achieving an AUROC of at least 0.89 and surpassing several different baselines. We then show that the embedding-vectors for verbs and nouns learned by the two CF models can be quantized (via application of k-means clustering) with minimal loss of performance on the prediction task while only using a small number of verb and noun clusters (relative to the number of distinct verbs and nouns). Finally we evaluate the alignment between the quantized embedding vectors for verbs and the Levin verb classes, finding that the alignment surpassed several randomized baselines. We conclude by discussing how model-based CF algorithms might be applied to learning restrictions on constituent selection between various lexical categories and how these (learned) models could then be used to augment a (rule-based) constituency grammar.</abstract>
    <identifier type="citekey">indurkhya-2021-using</identifier>
    <location>
        <url>https://aclanthology.org/2021.ranlp-1.71</url>
    </location>
    <part>
        <date>2021-sep</date>
        <extent unit="page">
            <start>629</start>
            <end>639</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Using Collaborative Filtering to Model Argument Selection
%A Indurkhya, Sagar
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 sep
%I INCOMA Ltd.
%C Held Online
%F indurkhya-2021-using
%X This study evaluates whether model-based Collaborative Filtering (CF) algorithms, which have been extensively studied and widely used to build recommender systems, can be used to predict which common nouns a predicate can take as its complement. We find that, when trained on verb-noun co-occurrence data drawn from the Corpus of Contemporary American-English (COCA), two popular model-based CF algorithms, Singular Value Decomposition and Non-negative Matrix Factorization, perform well on this task, each achieving an AUROC of at least 0.89 and surpassing several different baselines. We then show that the embedding-vectors for verbs and nouns learned by the two CF models can be quantized (via application of k-means clustering) with minimal loss of performance on the prediction task while only using a small number of verb and noun clusters (relative to the number of distinct verbs and nouns). Finally we evaluate the alignment between the quantized embedding vectors for verbs and the Levin verb classes, finding that the alignment surpassed several randomized baselines. We conclude by discussing how model-based CF algorithms might be applied to learning restrictions on constituent selection between various lexical categories and how these (learned) models could then be used to augment a (rule-based) constituency grammar.
%U https://aclanthology.org/2021.ranlp-1.71
%P 629-639

Markdown (Informal)

[Using Collaborative Filtering to Model Argument Selection](https://aclanthology.org/2021.ranlp-1.71) (Indurkhya, RANLP 2021)

• Using Collaborative Filtering to Model Argument Selection (Indurkhya, RANLP 2021)

ACL

• Sagar Indurkhya. 2021. Using Collaborative Filtering to Model Argument Selection. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 629–639, Held Online. INCOMA Ltd..