@inproceedings{tabasi-etal-2022-exploiting,
title = "Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context Task",
author = "Tabasi, Mohsen and
Rezaee, Kiamehr and
Pilehvar, Mohammad Taher",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.36",
doi = "10.18653/v1/2022.acl-short.36",
pages = "325--332",
abstract = "As a recent development in few-shot learning, prompt-based techniques have demonstrated promising potential in a variety of natural language processing tasks. However, despite proving competitive on most tasks in the GLUE and SuperGLUE benchmarks, existing prompt-based techniques fail on the semantic distinction task of the Word-in-Context (WiC) dataset. Specifically, none of the existing few-shot approaches (including the in-context learning of GPT-3) can attain a performance that is meaningfully different from the random baseline. Trying to fill this gap, we propose a new prompting technique, based on similarity metrics, which boosts few-shot performance to the level of fully supervised methods. Our simple adaptation shows that the failure of existing prompt-based techniques in semantic distinction is due to their improper configuration, rather than lack of relevant knowledge in the representations. We also show that this approach can be effectively extended to other downstream tasks for which a single prompt is sufficient.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tabasi-etal-2022-exploiting">
<titleInfo>
<title>Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohsen</namePart>
<namePart type="family">Tabasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiamehr</namePart>
<namePart type="family">Rezaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As a recent development in few-shot learning, prompt-based techniques have demonstrated promising potential in a variety of natural language processing tasks. However, despite proving competitive on most tasks in the GLUE and SuperGLUE benchmarks, existing prompt-based techniques fail on the semantic distinction task of the Word-in-Context (WiC) dataset. Specifically, none of the existing few-shot approaches (including the in-context learning of GPT-3) can attain a performance that is meaningfully different from the random baseline. Trying to fill this gap, we propose a new prompting technique, based on similarity metrics, which boosts few-shot performance to the level of fully supervised methods. Our simple adaptation shows that the failure of existing prompt-based techniques in semantic distinction is due to their improper configuration, rather than lack of relevant knowledge in the representations. We also show that this approach can be effectively extended to other downstream tasks for which a single prompt is sufficient.</abstract>
<identifier type="citekey">tabasi-etal-2022-exploiting</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.36</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.36</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>325</start>
<end>332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context Task
%A Tabasi, Mohsen
%A Rezaee, Kiamehr
%A Pilehvar, Mohammad Taher
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F tabasi-etal-2022-exploiting
%X As a recent development in few-shot learning, prompt-based techniques have demonstrated promising potential in a variety of natural language processing tasks. However, despite proving competitive on most tasks in the GLUE and SuperGLUE benchmarks, existing prompt-based techniques fail on the semantic distinction task of the Word-in-Context (WiC) dataset. Specifically, none of the existing few-shot approaches (including the in-context learning of GPT-3) can attain a performance that is meaningfully different from the random baseline. Trying to fill this gap, we propose a new prompting technique, based on similarity metrics, which boosts few-shot performance to the level of fully supervised methods. Our simple adaptation shows that the failure of existing prompt-based techniques in semantic distinction is due to their improper configuration, rather than lack of relevant knowledge in the representations. We also show that this approach can be effectively extended to other downstream tasks for which a single prompt is sufficient.
%R 10.18653/v1/2022.acl-short.36
%U https://aclanthology.org/2022.acl-short.36
%U https://doi.org/10.18653/v1/2022.acl-short.36
%P 325-332
Markdown (Informal)
[Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context Task](https://aclanthology.org/2022.acl-short.36) (Tabasi et al., ACL 2022)
ACL