@inproceedings{arora-etal-2021-low,
title = "Low-Rank Subspaces for Unsupervised Entity Linking",
author = "Arora, Akhil and
Garcia-Duran, Alberto and
West, Robert",
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.634",
doi = "10.18653/v1/2021.emnlp-main.634",
pages = "8037--8054",
abstract = "Entity linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not the case in numerous domains. We propose a light-weight and scalable entity linking method, Eigenthemes, that relies solely on the availability of entity names and a referent knowledge base. Eigenthemes exploits the fact that the entities that are truly mentioned in a document (the {``}gold entities{''}) tend to form a semantically dense subset of the set of all candidate entities in the document. Geometrically speaking, when representing entities as vectors via some given embedding, the gold entities tend to lie in a low-rank subspace of the full embedding space. Eigenthemes identifies this subspace using the singular value decomposition and scores candidate entities according to their proximity to the subspace. On the empirical front, we introduce multiple strong baselines that compare favorably to (and sometimes even outperform) the existing state of the art. Extensive experiments on benchmark datasets from a variety of real-world domains showcase the effectiveness of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arora-etal-2021-low">
<titleInfo>
<title>Low-Rank Subspaces for Unsupervised Entity Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Garcia-Duran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">West</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 linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not the case in numerous domains. We propose a light-weight and scalable entity linking method, Eigenthemes, that relies solely on the availability of entity names and a referent knowledge base. Eigenthemes exploits the fact that the entities that are truly mentioned in a document (the “gold entities”) tend to form a semantically dense subset of the set of all candidate entities in the document. Geometrically speaking, when representing entities as vectors via some given embedding, the gold entities tend to lie in a low-rank subspace of the full embedding space. Eigenthemes identifies this subspace using the singular value decomposition and scores candidate entities according to their proximity to the subspace. On the empirical front, we introduce multiple strong baselines that compare favorably to (and sometimes even outperform) the existing state of the art. Extensive experiments on benchmark datasets from a variety of real-world domains showcase the effectiveness of our approach.</abstract>
<identifier type="citekey">arora-etal-2021-low</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.634</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.634</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>8037</start>
<end>8054</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low-Rank Subspaces for Unsupervised Entity Linking
%A Arora, Akhil
%A Garcia-Duran, Alberto
%A West, Robert
%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 arora-etal-2021-low
%X Entity linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not the case in numerous domains. We propose a light-weight and scalable entity linking method, Eigenthemes, that relies solely on the availability of entity names and a referent knowledge base. Eigenthemes exploits the fact that the entities that are truly mentioned in a document (the “gold entities”) tend to form a semantically dense subset of the set of all candidate entities in the document. Geometrically speaking, when representing entities as vectors via some given embedding, the gold entities tend to lie in a low-rank subspace of the full embedding space. Eigenthemes identifies this subspace using the singular value decomposition and scores candidate entities according to their proximity to the subspace. On the empirical front, we introduce multiple strong baselines that compare favorably to (and sometimes even outperform) the existing state of the art. Extensive experiments on benchmark datasets from a variety of real-world domains showcase the effectiveness of our approach.
%R 10.18653/v1/2021.emnlp-main.634
%U https://aclanthology.org/2021.emnlp-main.634
%U https://doi.org/10.18653/v1/2021.emnlp-main.634
%P 8037-8054
Markdown (Informal)
[Low-Rank Subspaces for Unsupervised Entity Linking](https://aclanthology.org/2021.emnlp-main.634) (Arora et al., EMNLP 2021)
ACL
- Akhil Arora, Alberto Garcia-Duran, and Robert West. 2021. Low-Rank Subspaces for Unsupervised Entity Linking. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8037–8054, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.