@inproceedings{lee-etal-2022-really,
title = "Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods",
author = "Lee, Juhyuk and
Lee, Min-Joong and
Yang, June Yong and
Yang, Eunho",
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.282",
doi = "10.18653/v1/2022.naacl-main.282",
pages = "3849--3858",
abstract = "The ability to extract entities and their relations from unstructured text is essential for the automated maintenance of large-scale knowledge graphs. To keep a knowledge graph up-to-date, an extractor needs not only the ability to recall the triples it encountered during training, but also the ability to extract the new triples from the context that it has never seen before. In this paper, we show that although existing extraction models are able to easily memorize and recall already seen triples, they cannot generalize effectively for unseen triples. This alarming observation was previously unknown due to the composition of the test sets of the go-to benchmark datasets, which turns out to contain only 2{\%} unseen data, rendering them incapable to measure the generalization performance. To separately measure the generalization performance from the memorization performance, we emphasize unseen data by rearranging datasets, sifting out training instances, or augmenting test sets. In addition to that, we present a simple yet effective augmentation technique to promote generalization of existing extraction models, and experimentally confirm that the proposed method can significantly increase the generalization performance of existing models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2022-really">
<titleInfo>
<title>Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juhyuk</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Joong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">June</namePart>
<namePart type="given">Yong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunho</namePart>
<namePart type="family">Yang</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>The ability to extract entities and their relations from unstructured text is essential for the automated maintenance of large-scale knowledge graphs. To keep a knowledge graph up-to-date, an extractor needs not only the ability to recall the triples it encountered during training, but also the ability to extract the new triples from the context that it has never seen before. In this paper, we show that although existing extraction models are able to easily memorize and recall already seen triples, they cannot generalize effectively for unseen triples. This alarming observation was previously unknown due to the composition of the test sets of the go-to benchmark datasets, which turns out to contain only 2% unseen data, rendering them incapable to measure the generalization performance. To separately measure the generalization performance from the memorization performance, we emphasize unseen data by rearranging datasets, sifting out training instances, or augmenting test sets. In addition to that, we present a simple yet effective augmentation technique to promote generalization of existing extraction models, and experimentally confirm that the proposed method can significantly increase the generalization performance of existing models.</abstract>
<identifier type="citekey">lee-etal-2022-really</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.282</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.282</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3849</start>
<end>3858</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods
%A Lee, Juhyuk
%A Lee, Min-Joong
%A Yang, June Yong
%A Yang, Eunho
%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 lee-etal-2022-really
%X The ability to extract entities and their relations from unstructured text is essential for the automated maintenance of large-scale knowledge graphs. To keep a knowledge graph up-to-date, an extractor needs not only the ability to recall the triples it encountered during training, but also the ability to extract the new triples from the context that it has never seen before. In this paper, we show that although existing extraction models are able to easily memorize and recall already seen triples, they cannot generalize effectively for unseen triples. This alarming observation was previously unknown due to the composition of the test sets of the go-to benchmark datasets, which turns out to contain only 2% unseen data, rendering them incapable to measure the generalization performance. To separately measure the generalization performance from the memorization performance, we emphasize unseen data by rearranging datasets, sifting out training instances, or augmenting test sets. In addition to that, we present a simple yet effective augmentation technique to promote generalization of existing extraction models, and experimentally confirm that the proposed method can significantly increase the generalization performance of existing models.
%R 10.18653/v1/2022.naacl-main.282
%U https://aclanthology.org/2022.naacl-main.282
%U https://doi.org/10.18653/v1/2022.naacl-main.282
%P 3849-3858
Markdown (Informal)
[Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods](https://aclanthology.org/2022.naacl-main.282) (Lee et al., NAACL 2022)
ACL