@inproceedings{thai-etal-2021-simultaneously,
title = "Simultaneously Self-Attending to Text and Entities for Knowledge-Informed Text Representations",
author = "Thai, Dung and
Thirukovalluru, Raghuveer and
Bansal, Trapit and
McCallum, Andrew",
editor = "Rogers, Anna and
Calixto, Iacer and
Vuli{\'c}, Ivan and
Saphra, Naomi and
Kassner, Nora and
Camburu, Oana-Maria and
Bansal, Trapit and
Shwartz, Vered",
booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.repl4nlp-1.25",
doi = "10.18653/v1/2021.repl4nlp-1.25",
pages = "241--247",
abstract = "Pre-trained language models have emerged as highly successful methods for learning good text representations. However, the amount of structured knowledge retained in such models, and how (if at all) it can be extracted, remains an open question. In this work, we aim at directly learning text representations which leverage structured knowledge about entities mentioned in the text. This can be particularly beneficial for downstream tasks which are knowledge-intensive. Our approach utilizes self-attention between words in the text and knowledge graph (KG) entities mentioned in the text. While existing methods require entity-linked data for pre-training, we train using a mention-span masking objective and a candidate ranking objective {--} which doesn{'}t require any entity-links and only assumes access to an alias table for retrieving candidates, enabling large-scale pre-training. We show that the proposed model learns knowledge-informed text representations that yield improvements on the downstream tasks over existing methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thai-etal-2021-simultaneously">
<titleInfo>
<title>Simultaneously Self-Attending to Text and Entities for Knowledge-Informed Text Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dung</namePart>
<namePart type="family">Thai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghuveer</namePart>
<namePart type="family">Thirukovalluru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iacer</namePart>
<namePart type="family">Calixto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana-Maria</namePart>
<namePart type="family">Camburu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models have emerged as highly successful methods for learning good text representations. However, the amount of structured knowledge retained in such models, and how (if at all) it can be extracted, remains an open question. In this work, we aim at directly learning text representations which leverage structured knowledge about entities mentioned in the text. This can be particularly beneficial for downstream tasks which are knowledge-intensive. Our approach utilizes self-attention between words in the text and knowledge graph (KG) entities mentioned in the text. While existing methods require entity-linked data for pre-training, we train using a mention-span masking objective and a candidate ranking objective – which doesn’t require any entity-links and only assumes access to an alias table for retrieving candidates, enabling large-scale pre-training. We show that the proposed model learns knowledge-informed text representations that yield improvements on the downstream tasks over existing methods.</abstract>
<identifier type="citekey">thai-etal-2021-simultaneously</identifier>
<identifier type="doi">10.18653/v1/2021.repl4nlp-1.25</identifier>
<location>
<url>https://aclanthology.org/2021.repl4nlp-1.25</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>241</start>
<end>247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simultaneously Self-Attending to Text and Entities for Knowledge-Informed Text Representations
%A Thai, Dung
%A Thirukovalluru, Raghuveer
%A Bansal, Trapit
%A McCallum, Andrew
%Y Rogers, Anna
%Y Calixto, Iacer
%Y Vulić, Ivan
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Camburu, Oana-Maria
%Y Bansal, Trapit
%Y Shwartz, Vered
%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F thai-etal-2021-simultaneously
%X Pre-trained language models have emerged as highly successful methods for learning good text representations. However, the amount of structured knowledge retained in such models, and how (if at all) it can be extracted, remains an open question. In this work, we aim at directly learning text representations which leverage structured knowledge about entities mentioned in the text. This can be particularly beneficial for downstream tasks which are knowledge-intensive. Our approach utilizes self-attention between words in the text and knowledge graph (KG) entities mentioned in the text. While existing methods require entity-linked data for pre-training, we train using a mention-span masking objective and a candidate ranking objective – which doesn’t require any entity-links and only assumes access to an alias table for retrieving candidates, enabling large-scale pre-training. We show that the proposed model learns knowledge-informed text representations that yield improvements on the downstream tasks over existing methods.
%R 10.18653/v1/2021.repl4nlp-1.25
%U https://aclanthology.org/2021.repl4nlp-1.25
%U https://doi.org/10.18653/v1/2021.repl4nlp-1.25
%P 241-247
Markdown (Informal)
[Simultaneously Self-Attending to Text and Entities for Knowledge-Informed Text Representations](https://aclanthology.org/2021.repl4nlp-1.25) (Thai et al., RepL4NLP 2021)
ACL