@inproceedings{siino-2024-deberta,
title = "{D}e{BERT}a at {S}em{E}val-2024 Task 9: Using {D}e{BERT}a for Defying Common Sense",
author = "Siino, Marco",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.45",
pages = "291--297",
abstract = "The widespread success of language models has spurred the natural language processing (NLP) community to tackle tasks demanding implicit and intricate reasoning, drawing upon human-like common-sense mechanisms. While endeavors in vertical thinking tasks have garnered considerable attention, there has been a relative dearth of exploration in lateral thinking puzzles. To address this gap, we introduce BRAINTEASER: a multiple-choice Question Answering task meticulously crafted to evaluate the model{'}s capacity for lateral thinking and its ability to challenge default common-sense associations. At the SemEval-2024 Task 9, for the first subtask (i.e., Sentence Puzzle) the organizers asked the participants to develop models able to reply to multi-answer brain-teasing questions. For this purpose, we propose the application of a DeBERTa model in a zero-shot configuration. Our proposed approach is able to reach an overall score of 0.250. Suggesting a significant room for improvements in future works.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siino-2024-deberta">
<titleInfo>
<title>DeBERTa at SemEval-2024 Task 9: Using DeBERTa for Defying Common Sense</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Siino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The widespread success of language models has spurred the natural language processing (NLP) community to tackle tasks demanding implicit and intricate reasoning, drawing upon human-like common-sense mechanisms. While endeavors in vertical thinking tasks have garnered considerable attention, there has been a relative dearth of exploration in lateral thinking puzzles. To address this gap, we introduce BRAINTEASER: a multiple-choice Question Answering task meticulously crafted to evaluate the model’s capacity for lateral thinking and its ability to challenge default common-sense associations. At the SemEval-2024 Task 9, for the first subtask (i.e., Sentence Puzzle) the organizers asked the participants to develop models able to reply to multi-answer brain-teasing questions. For this purpose, we propose the application of a DeBERTa model in a zero-shot configuration. Our proposed approach is able to reach an overall score of 0.250. Suggesting a significant room for improvements in future works.</abstract>
<identifier type="citekey">siino-2024-deberta</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.45</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>291</start>
<end>297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeBERTa at SemEval-2024 Task 9: Using DeBERTa for Defying Common Sense
%A Siino, Marco
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F siino-2024-deberta
%X The widespread success of language models has spurred the natural language processing (NLP) community to tackle tasks demanding implicit and intricate reasoning, drawing upon human-like common-sense mechanisms. While endeavors in vertical thinking tasks have garnered considerable attention, there has been a relative dearth of exploration in lateral thinking puzzles. To address this gap, we introduce BRAINTEASER: a multiple-choice Question Answering task meticulously crafted to evaluate the model’s capacity for lateral thinking and its ability to challenge default common-sense associations. At the SemEval-2024 Task 9, for the first subtask (i.e., Sentence Puzzle) the organizers asked the participants to develop models able to reply to multi-answer brain-teasing questions. For this purpose, we propose the application of a DeBERTa model in a zero-shot configuration. Our proposed approach is able to reach an overall score of 0.250. Suggesting a significant room for improvements in future works.
%U https://aclanthology.org/2024.semeval-1.45
%P 291-297
Markdown (Informal)
[DeBERTa at SemEval-2024 Task 9: Using DeBERTa for Defying Common Sense](https://aclanthology.org/2024.semeval-1.45) (Siino, SemEval 2024)
ACL