@inproceedings{liu-etal-2021-activeea,
title = "{A}ctive{EA}: Active Learning for Neural Entity Alignment",
author = "Liu, Bing and
Scells, Harrisen and
Zuccon, Guido and
Hua, Wen and
Zhao, Genghong",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.270",
doi = "10.18653/v1/2021.emnlp-main.270",
pages = "3364--3374",
abstract = "Entity Alignment (EA) aims to match equivalent entities across different Knowledge Graphs (KGs) and is an essential step of KG fusion. Current mainstream methods {--} neural EA models {--} rely on training with seed alignment, i.e., a set of pre-aligned entity pairs which are very costly to annotate. In this paper, we devise a novel Active Learning (AL) framework for neural EA, aiming to create highly informative seed alignment to obtain more effective EA models with less annotation cost. Our framework tackles two main challenges encountered when applying AL to EA: (1) How to exploit dependencies between entities within the AL strategy. Most AL strategies assume that the data instances to sample are independent and identically distributed. However, entities in KGs are related. To address this challenge, we propose a structure-aware uncertainty sampling strategy that can measure the uncertainty of each entity as well as its impact on its neighbour entities in the KG. (2) How to recognise entities that appear in one KG but not in the other KG (i.e., bachelors). Identifying bachelors would likely save annotation budget. To address this challenge, we devise a bachelor recognizer paying attention to alleviate the effect of sampling bias. Empirical results show that our proposed AL strategy can significantly improve sampling quality with good generality across different datasets, EA models and amount of bachelors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-activeea">
<titleInfo>
<title>ActiveEA: Active Learning for Neural Entity Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harrisen</namePart>
<namePart type="family">Scells</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Zuccon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genghong</namePart>
<namePart type="family">Zhao</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>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Entity Alignment (EA) aims to match equivalent entities across different Knowledge Graphs (KGs) and is an essential step of KG fusion. Current mainstream methods – neural EA models – rely on training with seed alignment, i.e., a set of pre-aligned entity pairs which are very costly to annotate. In this paper, we devise a novel Active Learning (AL) framework for neural EA, aiming to create highly informative seed alignment to obtain more effective EA models with less annotation cost. Our framework tackles two main challenges encountered when applying AL to EA: (1) How to exploit dependencies between entities within the AL strategy. Most AL strategies assume that the data instances to sample are independent and identically distributed. However, entities in KGs are related. To address this challenge, we propose a structure-aware uncertainty sampling strategy that can measure the uncertainty of each entity as well as its impact on its neighbour entities in the KG. (2) How to recognise entities that appear in one KG but not in the other KG (i.e., bachelors). Identifying bachelors would likely save annotation budget. To address this challenge, we devise a bachelor recognizer paying attention to alleviate the effect of sampling bias. Empirical results show that our proposed AL strategy can significantly improve sampling quality with good generality across different datasets, EA models and amount of bachelors.</abstract>
<identifier type="citekey">liu-etal-2021-activeea</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.270</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.270</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3364</start>
<end>3374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ActiveEA: Active Learning for Neural Entity Alignment
%A Liu, Bing
%A Scells, Harrisen
%A Zuccon, Guido
%A Hua, Wen
%A Zhao, Genghong
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%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 liu-etal-2021-activeea
%X Entity Alignment (EA) aims to match equivalent entities across different Knowledge Graphs (KGs) and is an essential step of KG fusion. Current mainstream methods – neural EA models – rely on training with seed alignment, i.e., a set of pre-aligned entity pairs which are very costly to annotate. In this paper, we devise a novel Active Learning (AL) framework for neural EA, aiming to create highly informative seed alignment to obtain more effective EA models with less annotation cost. Our framework tackles two main challenges encountered when applying AL to EA: (1) How to exploit dependencies between entities within the AL strategy. Most AL strategies assume that the data instances to sample are independent and identically distributed. However, entities in KGs are related. To address this challenge, we propose a structure-aware uncertainty sampling strategy that can measure the uncertainty of each entity as well as its impact on its neighbour entities in the KG. (2) How to recognise entities that appear in one KG but not in the other KG (i.e., bachelors). Identifying bachelors would likely save annotation budget. To address this challenge, we devise a bachelor recognizer paying attention to alleviate the effect of sampling bias. Empirical results show that our proposed AL strategy can significantly improve sampling quality with good generality across different datasets, EA models and amount of bachelors.
%R 10.18653/v1/2021.emnlp-main.270
%U https://aclanthology.org/2021.emnlp-main.270
%U https://doi.org/10.18653/v1/2021.emnlp-main.270
%P 3364-3374
Markdown (Informal)
[ActiveEA: Active Learning for Neural Entity Alignment](https://aclanthology.org/2021.emnlp-main.270) (Liu et al., EMNLP 2021)
ACL
- Bing Liu, Harrisen Scells, Guido Zuccon, Wen Hua, and Genghong Zhao. 2021. ActiveEA: Active Learning for Neural Entity Alignment. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3364–3374, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.