@inproceedings{wu-etal-2023-hence,
title = "Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning",
author = "Wu, Yongkang and
Han, Meng and
Zhu, Yutao and
Li, Lei and
Zhang, Xinyu and
Lai, Ruofei and
Li, Xiaoguang and
Ren, Yuanhang and
Dou, Zhicheng and
Cao, Zhao",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.148",
doi = "10.18653/v1/2023.findings-acl.148",
pages = "2347--2367",
abstract = "Syllogistic reasoning, a typical form of deductive reasoning, is a critical capability widely required in natural language understanding tasks, such as text entailment and question answering. To better facilitate research on syllogistic reasoning, we develop a benchmark called SylloBase that differs from existing syllogistic datasets in three aspects: (1) Covering a complete taxonomy of syllogism reasoning patterns; (2) Containing both automatically and manually constructed samples; and (3) Involving both the generation and understanding tasks. We automatically construct 50k template-based syllogism samples by mining syllogism patterns from Wikidata and ConceptNet. To improve our dataset{'}s naturalness and challenge, we apply GPT-3 to paraphrase the template-based data and further manually rewrite 1,000 samples as the test set. State-of-the-art pre-trained language models can achieve the best generation ROUGE-L of 38.72 by T5 and the best multi-choice accuracy of 72.77{\%} by RoBERTa on SylloBase, which indicates the great challenge of learning diverse syllogistic reasoning types on SylloBase. Our datasets are released at \url{https://github.com/casually-PYlearner/SYLLOBASE}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-hence">
<titleInfo>
<title>Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongkang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruofei</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoguang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanhang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Cao</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Syllogistic reasoning, a typical form of deductive reasoning, is a critical capability widely required in natural language understanding tasks, such as text entailment and question answering. To better facilitate research on syllogistic reasoning, we develop a benchmark called SylloBase that differs from existing syllogistic datasets in three aspects: (1) Covering a complete taxonomy of syllogism reasoning patterns; (2) Containing both automatically and manually constructed samples; and (3) Involving both the generation and understanding tasks. We automatically construct 50k template-based syllogism samples by mining syllogism patterns from Wikidata and ConceptNet. To improve our dataset’s naturalness and challenge, we apply GPT-3 to paraphrase the template-based data and further manually rewrite 1,000 samples as the test set. State-of-the-art pre-trained language models can achieve the best generation ROUGE-L of 38.72 by T5 and the best multi-choice accuracy of 72.77% by RoBERTa on SylloBase, which indicates the great challenge of learning diverse syllogistic reasoning types on SylloBase. Our datasets are released at https://github.com/casually-PYlearner/SYLLOBASE.</abstract>
<identifier type="citekey">wu-etal-2023-hence</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.148</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.148</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2347</start>
<end>2367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning
%A Wu, Yongkang
%A Han, Meng
%A Zhu, Yutao
%A Li, Lei
%A Zhang, Xinyu
%A Lai, Ruofei
%A Li, Xiaoguang
%A Ren, Yuanhang
%A Dou, Zhicheng
%A Cao, Zhao
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wu-etal-2023-hence
%X Syllogistic reasoning, a typical form of deductive reasoning, is a critical capability widely required in natural language understanding tasks, such as text entailment and question answering. To better facilitate research on syllogistic reasoning, we develop a benchmark called SylloBase that differs from existing syllogistic datasets in three aspects: (1) Covering a complete taxonomy of syllogism reasoning patterns; (2) Containing both automatically and manually constructed samples; and (3) Involving both the generation and understanding tasks. We automatically construct 50k template-based syllogism samples by mining syllogism patterns from Wikidata and ConceptNet. To improve our dataset’s naturalness and challenge, we apply GPT-3 to paraphrase the template-based data and further manually rewrite 1,000 samples as the test set. State-of-the-art pre-trained language models can achieve the best generation ROUGE-L of 38.72 by T5 and the best multi-choice accuracy of 72.77% by RoBERTa on SylloBase, which indicates the great challenge of learning diverse syllogistic reasoning types on SylloBase. Our datasets are released at https://github.com/casually-PYlearner/SYLLOBASE.
%R 10.18653/v1/2023.findings-acl.148
%U https://aclanthology.org/2023.findings-acl.148
%U https://doi.org/10.18653/v1/2023.findings-acl.148
%P 2347-2367
Markdown (Informal)
[Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning](https://aclanthology.org/2023.findings-acl.148) (Wu et al., Findings 2023)
ACL
- Yongkang Wu, Meng Han, Yutao Zhu, Lei Li, Xinyu Zhang, Ruofei Lai, Xiaoguang Li, Yuanhang Ren, Zhicheng Dou, and Zhao Cao. 2023. Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2347–2367, Toronto, Canada. Association for Computational Linguistics.