@inproceedings{ralethe-buys-2022-generic,
title = "Generic Overgeneralization in Pre-trained Language Models",
author = "Ralethe, Sello and
Buys, Jan",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.282",
pages = "3187--3196",
abstract = "Generic statements such as {``}ducks lay eggs{''} make claims about kinds, e.g., ducks as a category. The generic overgeneralization effect refers to the inclination to accept false universal generalizations such as {``}all ducks lay eggs{''} or {``}all lions have manes{''} as true. In this paper, we investigate the generic overgeneralization effect in pre-trained language models experimentally. We show that pre-trained language models suffer from overgeneralization and tend to treat quantified generic statements such as {``}all ducks lay eggs{''} as if they were true generics. Furthermore, we demonstrate how knowledge embedding methods can lessen this effect by injecting factual knowledge about kinds into pre-trained language models. To this end, we source factual knowledge about two types of generics, minority characteristic generics and majority characteristic generics, and inject this knowledge using a knowledge embedding model. Our results show that knowledge injection reduces, but does not eliminate, generic overgeneralization, and that majority characteristic generics of kinds are more susceptible to overgeneralization bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ralethe-buys-2022-generic">
<titleInfo>
<title>Generic Overgeneralization in Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sello</namePart>
<namePart type="family">Ralethe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Buys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generic statements such as “ducks lay eggs” make claims about kinds, e.g., ducks as a category. The generic overgeneralization effect refers to the inclination to accept false universal generalizations such as “all ducks lay eggs” or “all lions have manes” as true. In this paper, we investigate the generic overgeneralization effect in pre-trained language models experimentally. We show that pre-trained language models suffer from overgeneralization and tend to treat quantified generic statements such as “all ducks lay eggs” as if they were true generics. Furthermore, we demonstrate how knowledge embedding methods can lessen this effect by injecting factual knowledge about kinds into pre-trained language models. To this end, we source factual knowledge about two types of generics, minority characteristic generics and majority characteristic generics, and inject this knowledge using a knowledge embedding model. Our results show that knowledge injection reduces, but does not eliminate, generic overgeneralization, and that majority characteristic generics of kinds are more susceptible to overgeneralization bias.</abstract>
<identifier type="citekey">ralethe-buys-2022-generic</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.282</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3187</start>
<end>3196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generic Overgeneralization in Pre-trained Language Models
%A Ralethe, Sello
%A Buys, Jan
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F ralethe-buys-2022-generic
%X Generic statements such as “ducks lay eggs” make claims about kinds, e.g., ducks as a category. The generic overgeneralization effect refers to the inclination to accept false universal generalizations such as “all ducks lay eggs” or “all lions have manes” as true. In this paper, we investigate the generic overgeneralization effect in pre-trained language models experimentally. We show that pre-trained language models suffer from overgeneralization and tend to treat quantified generic statements such as “all ducks lay eggs” as if they were true generics. Furthermore, we demonstrate how knowledge embedding methods can lessen this effect by injecting factual knowledge about kinds into pre-trained language models. To this end, we source factual knowledge about two types of generics, minority characteristic generics and majority characteristic generics, and inject this knowledge using a knowledge embedding model. Our results show that knowledge injection reduces, but does not eliminate, generic overgeneralization, and that majority characteristic generics of kinds are more susceptible to overgeneralization bias.
%U https://aclanthology.org/2022.coling-1.282
%P 3187-3196
Markdown (Informal)
[Generic Overgeneralization in Pre-trained Language Models](https://aclanthology.org/2022.coling-1.282) (Ralethe & Buys, COLING 2022)
ACL