Few-Shot Document-Level Relation Extraction (Extended Abstract)

被引：0

作者：

Popovic, Nicholas ^{[1
]}

Faerber, Michael ^{[1
]}

机构：

[1] Karlsruhe Inst Technol KIT, Inst AIFB, Karlsruhe, Germany

来源：

ADVANCES IN ARTIFICIAL INTELLIGENCE, KI 2023 | 2023年 / 14236卷

关键词：

Information extraction; Deep learning; Natural language processing;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark. As opposed to existing benchmarks which are built on sentence-level relation extraction corpora, we argue that document-level corpora provide more realism, particularly regarding none-of-the-above (NOTA) distributions. We adapt the state-of-the-art sentence-level method MNAV to the document-level and develop it further for improved domain adaptation. We find FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set. The data, code, and trained models are available online at https://github.com/nicpopovic/FREDo. Original venue: NAACL'22 [6].

引用

页码：257 / 260

页数：4

共 13 条

[1]

Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171

[2]

Gao TY, 2019, 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019), P6250

[3] A Novel Document-Level Relation Extraction Method Based on BERT and Entity Information [J].

Han, Xiaoyu ;

Wang, Lei .

IEEE ACCESS, 2020, 8 (96912-96919) :96912-96919

[4]

Han X, 2018, Arxiv, DOI arXiv:1810.10147

[5]

Luan Y, 2018, 2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), P3219

[6]

Popovic N, 2022, NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, P5733

[7] Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes [J].

Sabo, Ofer ;

Elazar, Yanai ;

Goldberg, Yoav ;

Dagan, Ido .

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2021, 9 :691-706

[8]

Soares LB, 2019, 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), P2895

[9]

Xiao YX, 2022, Arxiv, DOI arXiv:2109.12093

[10]

Xu B., 2021, arXiv, DOI DOI 10.1609/AAAI.V35I16.17665

← 1 2 →