@inproceedings{mahowald-2023-discerning,
title = "A Discerning Several Thousand Judgments: {GPT}-3 Rates the Article + Adjective + Numeral + Noun Construction",
author = "Mahowald, Kyle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.20",
doi = "10.18653/v1/2023.eacl-main.20",
pages = "265--273",
abstract = "Knowledge of syntax includes knowledge of rare, idiosyncratic constructions. LLMs must overcome frequency biases in order to master such constructions. In this study, I prompt GPT-3 to give acceptability judgments on the English-language Article + Adjective + Numeral + Noun construction (e.g., {``}a lovely five days{''}). I validate the prompt using the CoLA corpus of acceptability judgments and then zero in on the AANN construction. I compare GPT- 3{'}s judgments to crowdsourced human judgments on a subset of sentences. GPT-3{'}s judgments are broadly similar to human judgments and generally align with proposed constraints in the literature but, in some cases, GPT-3{'}s judgments and human judgments diverge from the literature and from each other.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahowald-2023-discerning">
<titleInfo>
<title>A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Mahowald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge of syntax includes knowledge of rare, idiosyncratic constructions. LLMs must overcome frequency biases in order to master such constructions. In this study, I prompt GPT-3 to give acceptability judgments on the English-language Article + Adjective + Numeral + Noun construction (e.g., “a lovely five days”). I validate the prompt using the CoLA corpus of acceptability judgments and then zero in on the AANN construction. I compare GPT- 3’s judgments to crowdsourced human judgments on a subset of sentences. GPT-3’s judgments are broadly similar to human judgments and generally align with proposed constraints in the literature but, in some cases, GPT-3’s judgments and human judgments diverge from the literature and from each other.</abstract>
<identifier type="citekey">mahowald-2023-discerning</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.20</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.20</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>265</start>
<end>273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction
%A Mahowald, Kyle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F mahowald-2023-discerning
%X Knowledge of syntax includes knowledge of rare, idiosyncratic constructions. LLMs must overcome frequency biases in order to master such constructions. In this study, I prompt GPT-3 to give acceptability judgments on the English-language Article + Adjective + Numeral + Noun construction (e.g., “a lovely five days”). I validate the prompt using the CoLA corpus of acceptability judgments and then zero in on the AANN construction. I compare GPT- 3’s judgments to crowdsourced human judgments on a subset of sentences. GPT-3’s judgments are broadly similar to human judgments and generally align with proposed constraints in the literature but, in some cases, GPT-3’s judgments and human judgments diverge from the literature and from each other.
%R 10.18653/v1/2023.eacl-main.20
%U https://aclanthology.org/2023.eacl-main.20
%U https://doi.org/10.18653/v1/2023.eacl-main.20
%P 265-273
Markdown (Informal)
[A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction](https://aclanthology.org/2023.eacl-main.20) (Mahowald, EACL 2023)
ACL