@inproceedings{li-etal-2022-instilling,
title = "Instilling Type Knowledge in Language Models via Multi-Task {QA}",
author = "Li, Shuyang and
Sridhar, Mukund and
Satya Prakash, Chandana and
Cao, Jin and
Hamza, Wael and
McAuley, Julian",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.45/",
doi = "10.18653/v1/2022.findings-naacl.45",
pages = "594--603",
abstract = "Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge{---}their \textit{types}.Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and incomplete labels. We introduce a method to instill fine-grained type knowledge in language models with text-to-text pre-training on type-centric questions leveraging knowledge base documents and knowledge graphs.We create the \textbf{WikiWiki} dataset: entities and passages from 10M Wikipedia articles linked to the Wikidata knowledge graph with 41K types.Models trained on WikiWiki achieve state-of-the-art performance in zero-shot dialog state tracking benchmarks, accurately infer entity types in Wikipedia articles, and can discover new types deemed useful by human judges."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-instilling">
<titleInfo>
<title>Instilling Type Knowledge in Language Models via Multi-Task QA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mukund</namePart>
<namePart type="family">Sridhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandana</namePart>
<namePart type="family">Satya Prakash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wael</namePart>
<namePart type="family">Hamza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">McAuley</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>Findings of the Association for Computational Linguistics: NAACL 2022</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>Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge—their types.Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and incomplete labels. We introduce a method to instill fine-grained type knowledge in language models with text-to-text pre-training on type-centric questions leveraging knowledge base documents and knowledge graphs.We create the WikiWiki dataset: entities and passages from 10M Wikipedia articles linked to the Wikidata knowledge graph with 41K types.Models trained on WikiWiki achieve state-of-the-art performance in zero-shot dialog state tracking benchmarks, accurately infer entity types in Wikipedia articles, and can discover new types deemed useful by human judges.</abstract>
<identifier type="citekey">li-etal-2022-instilling</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.45</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.45/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>594</start>
<end>603</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Instilling Type Knowledge in Language Models via Multi-Task QA
%A Li, Shuyang
%A Sridhar, Mukund
%A Satya Prakash, Chandana
%A Cao, Jin
%A Hamza, Wael
%A McAuley, Julian
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F li-etal-2022-instilling
%X Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge—their types.Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and incomplete labels. We introduce a method to instill fine-grained type knowledge in language models with text-to-text pre-training on type-centric questions leveraging knowledge base documents and knowledge graphs.We create the WikiWiki dataset: entities and passages from 10M Wikipedia articles linked to the Wikidata knowledge graph with 41K types.Models trained on WikiWiki achieve state-of-the-art performance in zero-shot dialog state tracking benchmarks, accurately infer entity types in Wikipedia articles, and can discover new types deemed useful by human judges.
%R 10.18653/v1/2022.findings-naacl.45
%U https://aclanthology.org/2022.findings-naacl.45/
%U https://doi.org/10.18653/v1/2022.findings-naacl.45
%P 594-603
Markdown (Informal)
[Instilling Type Knowledge in Language Models via Multi-Task QA](https://aclanthology.org/2022.findings-naacl.45/) (Li et al., Findings 2022)
ACL
- Shuyang Li, Mukund Sridhar, Chandana Satya Prakash, Jin Cao, Wael Hamza, and Julian McAuley. 2022. Instilling Type Knowledge in Language Models via Multi-Task QA. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 594–603, Seattle, United States. Association for Computational Linguistics.