@inproceedings{wang-etal-2023-logical,
title = "Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models",
author = "Wang, Borui and
Huang, Qiuyuan and
Deb, Budhaditya and
Halfaker, Aaron and
Shao, Liqun and
McDuff, Daniel and
Awadallah, Ahmed Hassan and
Radev, Dragomir and
Gao, Jianfeng",
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.111",
doi = "10.18653/v1/2023.findings-acl.111",
pages = "1762--1773",
abstract = "Natural language contains rich logical structures and logical information, and correctly detecting and accurately understanding these logical structures and information underlying natural language texts is very crucial for NLP models{'} performance on many important NLU and NLG tasks. Existing pre-trained language models based on the transformer architecture mostly adopt a classical design for constructing their input embeddings that ignores the logical structures underlying natural language texts, thus limiting their ability to better capture and encode key logical information in the input sequences. To overcome such limitations, in this paper we first propose a novel approach to construct logic-aware input embeddings for transformer language models through a combination of logic detection, logic mapping and hierarchical logical projections, and then develop a corresponding new modeling paradigm that can upgrade existing transformer language models into logical transformers to boost their performance on different NLU and NLG tasks. Our empirical experiments on four important and challenging NLU and NLG tasks demonstrate that our proposed logical transformer language models can achieve superior performance over their baseline transformer models through a deeper understanding of the logical structures of texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-logical">
<titleInfo>
<title>Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Borui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiuyuan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Budhaditya</namePart>
<namePart type="family">Deb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Halfaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqun</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">McDuff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Awadallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragomir</namePart>
<namePart type="family">Radev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Gao</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>Natural language contains rich logical structures and logical information, and correctly detecting and accurately understanding these logical structures and information underlying natural language texts is very crucial for NLP models’ performance on many important NLU and NLG tasks. Existing pre-trained language models based on the transformer architecture mostly adopt a classical design for constructing their input embeddings that ignores the logical structures underlying natural language texts, thus limiting their ability to better capture and encode key logical information in the input sequences. To overcome such limitations, in this paper we first propose a novel approach to construct logic-aware input embeddings for transformer language models through a combination of logic detection, logic mapping and hierarchical logical projections, and then develop a corresponding new modeling paradigm that can upgrade existing transformer language models into logical transformers to boost their performance on different NLU and NLG tasks. Our empirical experiments on four important and challenging NLU and NLG tasks demonstrate that our proposed logical transformer language models can achieve superior performance over their baseline transformer models through a deeper understanding of the logical structures of texts.</abstract>
<identifier type="citekey">wang-etal-2023-logical</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.111</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.111</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1762</start>
<end>1773</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models
%A Wang, Borui
%A Huang, Qiuyuan
%A Deb, Budhaditya
%A Halfaker, Aaron
%A Shao, Liqun
%A McDuff, Daniel
%A Awadallah, Ahmed Hassan
%A Radev, Dragomir
%A Gao, Jianfeng
%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 wang-etal-2023-logical
%X Natural language contains rich logical structures and logical information, and correctly detecting and accurately understanding these logical structures and information underlying natural language texts is very crucial for NLP models’ performance on many important NLU and NLG tasks. Existing pre-trained language models based on the transformer architecture mostly adopt a classical design for constructing their input embeddings that ignores the logical structures underlying natural language texts, thus limiting their ability to better capture and encode key logical information in the input sequences. To overcome such limitations, in this paper we first propose a novel approach to construct logic-aware input embeddings for transformer language models through a combination of logic detection, logic mapping and hierarchical logical projections, and then develop a corresponding new modeling paradigm that can upgrade existing transformer language models into logical transformers to boost their performance on different NLU and NLG tasks. Our empirical experiments on four important and challenging NLU and NLG tasks demonstrate that our proposed logical transformer language models can achieve superior performance over their baseline transformer models through a deeper understanding of the logical structures of texts.
%R 10.18653/v1/2023.findings-acl.111
%U https://aclanthology.org/2023.findings-acl.111
%U https://doi.org/10.18653/v1/2023.findings-acl.111
%P 1762-1773
Markdown (Informal)
[Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models](https://aclanthology.org/2023.findings-acl.111) (Wang et al., Findings 2023)
ACL
- Borui Wang, Qiuyuan Huang, Budhaditya Deb, Aaron Halfaker, Liqun Shao, Daniel McDuff, Ahmed Hassan Awadallah, Dragomir Radev, and Jianfeng Gao. 2023. Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1762–1773, Toronto, Canada. Association for Computational Linguistics.