@inproceedings{popovic-farber-2022-shot,
title = "Few-Shot Document-Level Relation Extraction",
author = {Popovic, Nicholas and
F{\"a}rber, Michael},
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.421",
doi = "10.18653/v1/2022.naacl-main.421",
pages = "5733--5746",
abstract = "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. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. 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 (\url{https://github.com/nicpopovic/FREDo}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popovic-farber-2022-shot">
<titleInfo>
<title>Few-Shot Document-Level Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Färber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. 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 (https://github.com/nicpopovic/FREDo).</abstract>
<identifier type="citekey">popovic-farber-2022-shot</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.421</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.421</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>5733</start>
<end>5746</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-Shot Document-Level Relation Extraction
%A Popovic, Nicholas
%A Färber, Michael
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F popovic-farber-2022-shot
%X 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. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. 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 (https://github.com/nicpopovic/FREDo).
%R 10.18653/v1/2022.naacl-main.421
%U https://aclanthology.org/2022.naacl-main.421
%U https://doi.org/10.18653/v1/2022.naacl-main.421
%P 5733-5746
Markdown (Informal)
[Few-Shot Document-Level Relation Extraction](https://aclanthology.org/2022.naacl-main.421) (Popovic & Färber, NAACL 2022)
ACL
- Nicholas Popovic and Michael Färber. 2022. Few-Shot Document-Level Relation Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5733–5746, Seattle, United States. Association for Computational Linguistics.