<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2021-mapre">
    <titleInfo>
        <title>MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Manqing</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chunguang</namePart>
        <namePart type="family">Pan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhipeng</namePart>
        <namePart type="family">Luo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural relation extraction models have shown promising results in recent years; however, the model performance drops dramatically given only a few training samples. Recent works try leveraging the advance in few-shot learning to solve the low resource problem, where they train label-agnostic models to directly compare the semantic similarities among context sentences in the embedding space. However, the label-aware information, i.e., the relation label that contains the semantic knowledge of the relation itself, is often neglected for prediction. In this work, we propose a framework considering both label-agnostic and label-aware semantic mapping information for low resource relation extraction. We show that incorporating the above two types of mapping information in both pretraining and fine-tuning can significantly improve the model performance on low-resource relation extraction tasks.</abstract>
    <identifier type="citekey">dong-etal-2021-mapre</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.212</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.212</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>2694</start>
            <end>2704</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction
%A Dong, Manqing
%A Pan, Chunguang
%A Luo, Zhipeng
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F dong-etal-2021-mapre
%X Neural relation extraction models have shown promising results in recent years; however, the model performance drops dramatically given only a few training samples. Recent works try leveraging the advance in few-shot learning to solve the low resource problem, where they train label-agnostic models to directly compare the semantic similarities among context sentences in the embedding space. However, the label-aware information, i.e., the relation label that contains the semantic knowledge of the relation itself, is often neglected for prediction. In this work, we propose a framework considering both label-agnostic and label-aware semantic mapping information for low resource relation extraction. We show that incorporating the above two types of mapping information in both pretraining and fine-tuning can significantly improve the model performance on low-resource relation extraction tasks.
%R 10.18653/v1/2021.emnlp-main.212
%U https://aclanthology.org/2021.emnlp-main.212
%U https://doi.org/10.18653/v1/2021.emnlp-main.212
%P 2694-2704

Markdown (Informal)

[MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction](https://aclanthology.org/2021.emnlp-main.212) (Dong et al., EMNLP 2021)

• MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction (Dong et al., EMNLP 2021)

ACL

• Manqing Dong, Chunguang Pan, and Zhipeng Luo. 2021. MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2694–2704, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.