@inproceedings{guo-etal-2023-decoding,
title = "Decoding Symbolism in Language Models",
author = "Guo, Meiqi and
Hwa, Rebecca and
Kovashka, Adriana",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.186",
doi = "10.18653/v1/2023.acl-long.186",
pages = "3311--3324",
abstract = "This work explores the feasibility of eliciting knowledge from language models (LMs) to decode symbolism, recognizing something (e.g.,roses) as a stand-in for another (e.g., love). We present our evaluative framework, Symbolism Analysis (SymbA), which compares LMs (e.g., RoBERTa, GPT-J) on different types of symbolism and analyze the outcomes along multiple metrics. Our findings suggest that conventional symbols are more reliably elicited from LMs while situated symbols are more challenging. Results also reveal the negative impact of the bias in pre-trained corpora. We further demonstrate that a simple re-ranking strategy can mitigate the bias and significantly improve model performances to be on par with human performances in some cases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2023-decoding">
<titleInfo>
<title>Decoding Symbolism in Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meiqi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriana</namePart>
<namePart type="family">Kovashka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work explores the feasibility of eliciting knowledge from language models (LMs) to decode symbolism, recognizing something (e.g.,roses) as a stand-in for another (e.g., love). We present our evaluative framework, Symbolism Analysis (SymbA), which compares LMs (e.g., RoBERTa, GPT-J) on different types of symbolism and analyze the outcomes along multiple metrics. Our findings suggest that conventional symbols are more reliably elicited from LMs while situated symbols are more challenging. Results also reveal the negative impact of the bias in pre-trained corpora. We further demonstrate that a simple re-ranking strategy can mitigate the bias and significantly improve model performances to be on par with human performances in some cases.</abstract>
<identifier type="citekey">guo-etal-2023-decoding</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.186</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.186</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3311</start>
<end>3324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decoding Symbolism in Language Models
%A Guo, Meiqi
%A Hwa, Rebecca
%A Kovashka, Adriana
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F guo-etal-2023-decoding
%X This work explores the feasibility of eliciting knowledge from language models (LMs) to decode symbolism, recognizing something (e.g.,roses) as a stand-in for another (e.g., love). We present our evaluative framework, Symbolism Analysis (SymbA), which compares LMs (e.g., RoBERTa, GPT-J) on different types of symbolism and analyze the outcomes along multiple metrics. Our findings suggest that conventional symbols are more reliably elicited from LMs while situated symbols are more challenging. Results also reveal the negative impact of the bias in pre-trained corpora. We further demonstrate that a simple re-ranking strategy can mitigate the bias and significantly improve model performances to be on par with human performances in some cases.
%R 10.18653/v1/2023.acl-long.186
%U https://aclanthology.org/2023.acl-long.186
%U https://doi.org/10.18653/v1/2023.acl-long.186
%P 3311-3324
Markdown (Informal)
[Decoding Symbolism in Language Models](https://aclanthology.org/2023.acl-long.186) (Guo et al., ACL 2023)
ACL
- Meiqi Guo, Rebecca Hwa, and Adriana Kovashka. 2023. Decoding Symbolism in Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3311–3324, Toronto, Canada. Association for Computational Linguistics.