@inproceedings{jia-li-2024-metaphor,
title = "Metaphor Detection with Context Enhancement and Curriculum Learning",
author = "Jia, Kaidi and
Li, Rongsheng",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.149",
pages = "2726--2737",
abstract = "Metaphor detection is a challenging task for natural language processing (NLP) systems. Previous works failed to sufficiently utilize the internal and external semantic relationships between target words and their context. Furthermore, they have faced challenges in tackling the problem of data sparseness due to the very limited available training data. To address these two challenges, we propose a novel model called MiceCL. By leveraging the difference between the literal meaning of the target word and the meaning of the sentence as the sentence external difference, MiceCL can better handle the semantic relationships. Additionally, we propose a curriculum learning framework for automatically assessing difficulty of the sentence with a pre-trained model. By starting from easy examples and gradually progressing to more difficult ones, we can ensure that the model will not deal with complex data when its ability is weak so that to avoid wasting limited data. Experimental results demonstrate that MiceCL achieves competitive performance across multiple datasets, with a significantly improved convergence speed compared to other models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-li-2024-metaphor">
<titleInfo>
<title>Metaphor Detection with Context Enhancement and Curriculum Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaidi</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongsheng</namePart>
<namePart type="family">Li</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 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</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>Metaphor detection is a challenging task for natural language processing (NLP) systems. Previous works failed to sufficiently utilize the internal and external semantic relationships between target words and their context. Furthermore, they have faced challenges in tackling the problem of data sparseness due to the very limited available training data. To address these two challenges, we propose a novel model called MiceCL. By leveraging the difference between the literal meaning of the target word and the meaning of the sentence as the sentence external difference, MiceCL can better handle the semantic relationships. Additionally, we propose a curriculum learning framework for automatically assessing difficulty of the sentence with a pre-trained model. By starting from easy examples and gradually progressing to more difficult ones, we can ensure that the model will not deal with complex data when its ability is weak so that to avoid wasting limited data. Experimental results demonstrate that MiceCL achieves competitive performance across multiple datasets, with a significantly improved convergence speed compared to other models.</abstract>
<identifier type="citekey">jia-li-2024-metaphor</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.149</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2726</start>
<end>2737</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Metaphor Detection with Context Enhancement and Curriculum Learning
%A Jia, Kaidi
%A Li, Rongsheng
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F jia-li-2024-metaphor
%X Metaphor detection is a challenging task for natural language processing (NLP) systems. Previous works failed to sufficiently utilize the internal and external semantic relationships between target words and their context. Furthermore, they have faced challenges in tackling the problem of data sparseness due to the very limited available training data. To address these two challenges, we propose a novel model called MiceCL. By leveraging the difference between the literal meaning of the target word and the meaning of the sentence as the sentence external difference, MiceCL can better handle the semantic relationships. Additionally, we propose a curriculum learning framework for automatically assessing difficulty of the sentence with a pre-trained model. By starting from easy examples and gradually progressing to more difficult ones, we can ensure that the model will not deal with complex data when its ability is weak so that to avoid wasting limited data. Experimental results demonstrate that MiceCL achieves competitive performance across multiple datasets, with a significantly improved convergence speed compared to other models.
%U https://aclanthology.org/2024.naacl-long.149
%P 2726-2737
Markdown (Informal)
[Metaphor Detection with Context Enhancement and Curriculum Learning](https://aclanthology.org/2024.naacl-long.149) (Jia & Li, NAACL 2024)
ACL
- Kaidi Jia and Rongsheng Li. 2024. Metaphor Detection with Context Enhancement and Curriculum Learning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2726–2737, Mexico City, Mexico. Association for Computational Linguistics.