<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="warstadt-etal-2020-blimp-benchmark">
    <titleInfo>
        <title>BLiMP: The Benchmark of Linguistic Minimal Pairs for English</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alex</namePart>
        <namePart type="family">Warstadt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alicia</namePart>
        <namePart type="family">Parrish</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haokun</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anhad</namePart>
        <namePart type="family">Mohananey</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sheng-Fu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samuel</namePart>
        <namePart type="given">R</namePart>
        <namePart type="family">Bowman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020</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 introduce The Benchmark of Linguistic Minimal Pairs (BLiMP),1 a challenge set for evaluating the linguistic knowledge of language models (LMs) on major grammatical phenomena in English. BLiMP consists of 67 individual datasets, each containing 1,000 minimal pairs—that is, pairs of minimally different sentences that contrast in grammatical acceptability and isolate specific phenomenon in syntax, morphology, or semantics. We generate the data according to linguist-crafted grammar templates, and human aggregate agreement with the labels is 96.4%. We evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs by observing whether they assign a higher probability to the acceptable sentence in each minimal pair. We find that state-of-the-art models identify morphological contrasts related to agreement reliably, but they struggle with some subtle semantic and syntactic phenomena, such as negative polarity items and extraction islands.</abstract>
    <identifier type="citekey">warstadt-etal-2020-blimp-benchmark</identifier>
    <identifier type="doi">10.1162/tacl_a_00321</identifier>
    <location>
        <url>https://aclanthology.org/2020.tacl-1.25/</url>
    </location>
    <part>
        <date>2020</date>
        <detail type="volume"><number>8</number></detail>
        <extent unit="page">
            <start>377</start>
            <end>392</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T BLiMP: The Benchmark of Linguistic Minimal Pairs for English
%A Warstadt, Alex
%A Parrish, Alicia
%A Liu, Haokun
%A Mohananey, Anhad
%A Peng, Wei
%A Wang, Sheng-Fu
%A Bowman, Samuel R.
%J Transactions of the Association for Computational Linguistics
%D 2020
%V 8
%I MIT Press
%C Cambridge, MA
%F warstadt-etal-2020-blimp-benchmark
%X We introduce The Benchmark of Linguistic Minimal Pairs (BLiMP),1 a challenge set for evaluating the linguistic knowledge of language models (LMs) on major grammatical phenomena in English. BLiMP consists of 67 individual datasets, each containing 1,000 minimal pairs—that is, pairs of minimally different sentences that contrast in grammatical acceptability and isolate specific phenomenon in syntax, morphology, or semantics. We generate the data according to linguist-crafted grammar templates, and human aggregate agreement with the labels is 96.4%. We evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs by observing whether they assign a higher probability to the acceptable sentence in each minimal pair. We find that state-of-the-art models identify morphological contrasts related to agreement reliably, but they struggle with some subtle semantic and syntactic phenomena, such as negative polarity items and extraction islands.
%R 10.1162/tacl_a_00321
%U https://aclanthology.org/2020.tacl-1.25/
%U https://doi.org/10.1162/tacl_a_00321
%P 377-392

Markdown (Informal)

[BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://aclanthology.org/2020.tacl-1.25/) (Warstadt et al., TACL 2020)

• BLiMP: The Benchmark of Linguistic Minimal Pairs for English (Warstadt et al., TACL 2020)

ACL

• Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mohananey, Wei Peng, Sheng-Fu Wang, and Samuel R. Bowman. 2020. BLiMP: The Benchmark of Linguistic Minimal Pairs for English. Transactions of the Association for Computational Linguistics, 8:377–392.