@inproceedings{chakrabarti-etal-2022-joint,
title = "Joint Completion and Alignment of Multilingual Knowledge Graphs",
author = "Chakrabarti, Soumen and
Singh, Harkanwar and
Lohiya, Shubham and
Jain, Prachi and
{Mausam}",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.817",
doi = "10.18653/v1/2022.emnlp-main.817",
pages = "11922--11938",
abstract = "Knowledge Graph Completion (KGC) predicts missing facts in an incomplete Knowledge Graph (KG). Multilingual KGs associate entities and relations with surface forms written in different languages. An entity or relation may be associated with distinct IDs in different KGs, necessitating entity alignment (EA) and relation alignment (RA). Many effective algorithms have been proposed for completion and alignment as separate tasks. Here we show that these tasks are synergistic and best solved together. Our multitask approach starts with a state-of-the-art KG embedding scheme, but adds a novel relation representation based on sets of embeddings of (subject, object) entity pairs. This representation leads to a new relation alignment loss term based on a maximal bipartite matching between two sets of embedding vectors. This loss is combined with traditional KGC loss and optionally, losses based on text embeddings of entity (and relation) names. In experiments over KGs in seven languages, we find that our system achieves large improvements in KGC compared to a strong completion model that combines known facts in all languages. It also outperforms strong EA and RA baselines, underscoring the value of joint alignment and completion.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakrabarti-etal-2022-joint">
<titleInfo>
<title>Joint Completion and Alignment of Multilingual Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumen</namePart>
<namePart type="family">Chakrabarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harkanwar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Lohiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prachi</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge Graph Completion (KGC) predicts missing facts in an incomplete Knowledge Graph (KG). Multilingual KGs associate entities and relations with surface forms written in different languages. An entity or relation may be associated with distinct IDs in different KGs, necessitating entity alignment (EA) and relation alignment (RA). Many effective algorithms have been proposed for completion and alignment as separate tasks. Here we show that these tasks are synergistic and best solved together. Our multitask approach starts with a state-of-the-art KG embedding scheme, but adds a novel relation representation based on sets of embeddings of (subject, object) entity pairs. This representation leads to a new relation alignment loss term based on a maximal bipartite matching between two sets of embedding vectors. This loss is combined with traditional KGC loss and optionally, losses based on text embeddings of entity (and relation) names. In experiments over KGs in seven languages, we find that our system achieves large improvements in KGC compared to a strong completion model that combines known facts in all languages. It also outperforms strong EA and RA baselines, underscoring the value of joint alignment and completion.</abstract>
<identifier type="citekey">chakrabarti-etal-2022-joint</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.817</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.817</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11922</start>
<end>11938</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Completion and Alignment of Multilingual Knowledge Graphs
%A Chakrabarti, Soumen
%A Singh, Harkanwar
%A Lohiya, Shubham
%A Jain, Prachi
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%A Mausam
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F chakrabarti-etal-2022-joint
%X Knowledge Graph Completion (KGC) predicts missing facts in an incomplete Knowledge Graph (KG). Multilingual KGs associate entities and relations with surface forms written in different languages. An entity or relation may be associated with distinct IDs in different KGs, necessitating entity alignment (EA) and relation alignment (RA). Many effective algorithms have been proposed for completion and alignment as separate tasks. Here we show that these tasks are synergistic and best solved together. Our multitask approach starts with a state-of-the-art KG embedding scheme, but adds a novel relation representation based on sets of embeddings of (subject, object) entity pairs. This representation leads to a new relation alignment loss term based on a maximal bipartite matching between two sets of embedding vectors. This loss is combined with traditional KGC loss and optionally, losses based on text embeddings of entity (and relation) names. In experiments over KGs in seven languages, we find that our system achieves large improvements in KGC compared to a strong completion model that combines known facts in all languages. It also outperforms strong EA and RA baselines, underscoring the value of joint alignment and completion.
%R 10.18653/v1/2022.emnlp-main.817
%U https://aclanthology.org/2022.emnlp-main.817
%U https://doi.org/10.18653/v1/2022.emnlp-main.817
%P 11922-11938
Markdown (Informal)
[Joint Completion and Alignment of Multilingual Knowledge Graphs](https://aclanthology.org/2022.emnlp-main.817) (Chakrabarti et al., EMNLP 2022)
ACL
- Soumen Chakrabarti, Harkanwar Singh, Shubham Lohiya, Prachi Jain, and Mausam. 2022. Joint Completion and Alignment of Multilingual Knowledge Graphs. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11922–11938, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.