@inproceedings{zeng-etal-2023-iekg,
title = "{IEKG}: A Commonsense Knowledge Graph for Idiomatic Expressions",
author = "Zeng, Ziheng and
Cheng, Kellen and
Nanniyur, Srihari and
Zhou, Jianing and
Bhat, Suma",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.881",
doi = "10.18653/v1/2023.emnlp-main.881",
pages = "14243--14264",
abstract = "Idiomatic expression (IE) processing and comprehension have challenged pre-trained language models (PTLMs) because their meanings are non-compositional. Unlike prior works that enable IE comprehension through fine-tuning PTLMs with sentences containing IEs, in this work, we construct IEKG, a commonsense knowledge graph for figurative interpretations of IEs. This extends the established ${ATOMIC}_{20}^{20}$ converting PTLMs into knowledge models (KMs) that encode and infer commonsense knowledge related to IE use. Experiments show that various PTLMs can be converted into KMs with IEKG. We verify the quality of IEKG and the ability of the trained KMs with automatic and human evaluation. Through applications in natural language understanding, we show that a PTLM injected with knowledge from IEKG exhibits improved IE comprehension ability and can generalize to IEs unseen during training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2023-iekg">
<titleInfo>
<title>IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziheng</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kellen</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srihari</namePart>
<namePart type="family">Nanniyur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianing</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suma</namePart>
<namePart type="family">Bhat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Idiomatic expression (IE) processing and comprehension have challenged pre-trained language models (PTLMs) because their meanings are non-compositional. Unlike prior works that enable IE comprehension through fine-tuning PTLMs with sentences containing IEs, in this work, we construct IEKG, a commonsense knowledge graph for figurative interpretations of IEs. This extends the established ATOMIC₂0²0 converting PTLMs into knowledge models (KMs) that encode and infer commonsense knowledge related to IE use. Experiments show that various PTLMs can be converted into KMs with IEKG. We verify the quality of IEKG and the ability of the trained KMs with automatic and human evaluation. Through applications in natural language understanding, we show that a PTLM injected with knowledge from IEKG exhibits improved IE comprehension ability and can generalize to IEs unseen during training.</abstract>
<identifier type="citekey">zeng-etal-2023-iekg</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.881</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.881</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14243</start>
<end>14264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions
%A Zeng, Ziheng
%A Cheng, Kellen
%A Nanniyur, Srihari
%A Zhou, Jianing
%A Bhat, Suma
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zeng-etal-2023-iekg
%X Idiomatic expression (IE) processing and comprehension have challenged pre-trained language models (PTLMs) because their meanings are non-compositional. Unlike prior works that enable IE comprehension through fine-tuning PTLMs with sentences containing IEs, in this work, we construct IEKG, a commonsense knowledge graph for figurative interpretations of IEs. This extends the established ATOMIC₂0²0 converting PTLMs into knowledge models (KMs) that encode and infer commonsense knowledge related to IE use. Experiments show that various PTLMs can be converted into KMs with IEKG. We verify the quality of IEKG and the ability of the trained KMs with automatic and human evaluation. Through applications in natural language understanding, we show that a PTLM injected with knowledge from IEKG exhibits improved IE comprehension ability and can generalize to IEs unseen during training.
%R 10.18653/v1/2023.emnlp-main.881
%U https://aclanthology.org/2023.emnlp-main.881
%U https://doi.org/10.18653/v1/2023.emnlp-main.881
%P 14243-14264
Markdown (Informal)
[IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions](https://aclanthology.org/2023.emnlp-main.881) (Zeng et al., EMNLP 2023)
ACL
- Ziheng Zeng, Kellen Cheng, Srihari Nanniyur, Jianing Zhou, and Suma Bhat. 2023. IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14243–14264, Singapore. Association for Computational Linguistics.