@inproceedings{rahimi-etal-2024-nimz,
title = "{NIMZ} at {S}em{E}val-2024 Task 9: Evaluating Methods in Solving Brainteasers Defying Commonsense",
author = "Rahimi, Zahra and
Shirzady, Mohammad Moein and
Taghavi, Zeinab and
Sameti, Hossein",
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-1.23",
doi = "10.18653/v1/2024.semeval-1.23",
pages = "148--154",
abstract = "The goal and dream of the artificial intelligence field have long been the development of intelligent systems or agents that mimic human behavior and thinking. Creativity is an essential trait in humans that is closely related to lateral thinking. The remarkable advancements in Language Models have led to extensive research on question-answering and explicit and implicit reasoning involving vertical thinking. However, there is an increasing need to shift focus towards research and development of models that can think laterally. One must step outside the traditional frame of commonsense concepts in lateral thinking to conclude. Task 9 of SemEval-2024 is Brainteaser (Jiang et al.,2024), which requires lateral thinking to answer riddle-like multiple-choice questions. In our study, we assessed the performance of various models for the Brainteaser task. We achieved an overall accuracy of 75{\%} for the Sentence Puzzle subtask and 66.7{\%} for the Word Puzzle subtask. All the codes, along with the links to our saved models, are available on our GitHub.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahimi-etal-2024-nimz">
<titleInfo>
<title>NIMZ at SemEval-2024 Task 9: Evaluating Methods in Solving Brainteasers Defying Commonsense</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zahra</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Moein</namePart>
<namePart type="family">Shirzady</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeinab</namePart>
<namePart type="family">Taghavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Sameti</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 goal and dream of the artificial intelligence field have long been the development of intelligent systems or agents that mimic human behavior and thinking. Creativity is an essential trait in humans that is closely related to lateral thinking. The remarkable advancements in Language Models have led to extensive research on question-answering and explicit and implicit reasoning involving vertical thinking. However, there is an increasing need to shift focus towards research and development of models that can think laterally. One must step outside the traditional frame of commonsense concepts in lateral thinking to conclude. Task 9 of SemEval-2024 is Brainteaser (Jiang et al.,2024), which requires lateral thinking to answer riddle-like multiple-choice questions. In our study, we assessed the performance of various models for the Brainteaser task. We achieved an overall accuracy of 75% for the Sentence Puzzle subtask and 66.7% for the Word Puzzle subtask. All the codes, along with the links to our saved models, are available on our GitHub.</abstract>
<identifier type="citekey">rahimi-etal-2024-nimz</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.23</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.23</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>148</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NIMZ at SemEval-2024 Task 9: Evaluating Methods in Solving Brainteasers Defying Commonsense
%A Rahimi, Zahra
%A Shirzady, Mohammad Moein
%A Taghavi, Zeinab
%A Sameti, Hossein
%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 rahimi-etal-2024-nimz
%X The goal and dream of the artificial intelligence field have long been the development of intelligent systems or agents that mimic human behavior and thinking. Creativity is an essential trait in humans that is closely related to lateral thinking. The remarkable advancements in Language Models have led to extensive research on question-answering and explicit and implicit reasoning involving vertical thinking. However, there is an increasing need to shift focus towards research and development of models that can think laterally. One must step outside the traditional frame of commonsense concepts in lateral thinking to conclude. Task 9 of SemEval-2024 is Brainteaser (Jiang et al.,2024), which requires lateral thinking to answer riddle-like multiple-choice questions. In our study, we assessed the performance of various models for the Brainteaser task. We achieved an overall accuracy of 75% for the Sentence Puzzle subtask and 66.7% for the Word Puzzle subtask. All the codes, along with the links to our saved models, are available on our GitHub.
%R 10.18653/v1/2024.semeval-1.23
%U https://aclanthology.org/2024.semeval-1.23
%U https://doi.org/10.18653/v1/2024.semeval-1.23
%P 148-154
Markdown (Informal)
[NIMZ at SemEval-2024 Task 9: Evaluating Methods in Solving Brainteasers Defying Commonsense](https://aclanthology.org/2024.semeval-1.23) (Rahimi et al., SemEval 2024)
ACL