Livio Baldini Soares,Nicholas FitzGerald,Jeffrey Ling,Tom Kwiatkowski
Abstract
General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task’s training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED
- Anthology ID:
- P19-1279
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen,David Traum,Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2895–2905
- Language:
- URL:
- https://aclanthology.org/P19-1279
- DOI:
- 10.18653/v1/P19-1279
- Bibkey:
- Cite (ACL):
- Livio Baldini Soares, Nicholas FitzGerald, Jeffrey Ling, and Tom Kwiatkowski. 2019. Matching the Blanks: Distributional Similarity for Relation Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2895–2905, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Matching the Blanks: Distributional Similarity for Relation Learning (Baldini Soares et al., ACL 2019)
- Copy Citation:
- PDF:
- https://aclanthology.org/P19-1279.pdf
- Video:
- https://aclanthology.org/P19-1279.mp4
- Code
- additional community code
- Data
- FewRel,SemEval-2010 Task-8,TACRED
Export citation
- BibTeX
- MODS XML
- Endnote
- Preformatted
@inproceedings{baldini-soares-etal-2019-matching, title = "Matching the Blanks: Distributional Similarity for Relation Learning", author = "Baldini Soares, Livio and FitzGerald, Nicholas and Ling, Jeffrey and Kwiatkowski, Tom", editor = "Korhonen, Anna and Traum, David and M{\`a}rquez, Llu{\'\i}s", booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2019", address = "Florence, Italy", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/P19-1279", doi = "10.18653/v1/P19-1279", pages = "2895--2905", abstract = "General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris{'} distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task{'}s training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED",}
Download as File
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="baldini-soares-etal-2019-matching"> <titleInfo> <title>Matching the Blanks: Distributional Similarity for Relation Learning</title> </titleInfo> <name type="personal"> <namePart type="given">Livio</namePart> <namePart type="family">Baldini Soares</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Nicholas</namePart> <namePart type="family">FitzGerald</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Jeffrey</namePart> <namePart type="family">Ling</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Tom</namePart> <namePart type="family">Kwiatkowski</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2019-07</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title> </titleInfo> <name type="personal"> <namePart type="given">Anna</namePart> <namePart type="family">Korhonen</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">David</namePart> <namePart type="family">Traum</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Lluís</namePart> <namePart type="family">Màrquez</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Florence, Italy</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task’s training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED</abstract> <identifier type="citekey">baldini-soares-etal-2019-matching</identifier> <identifier type="doi">10.18653/v1/P19-1279</identifier> <location> <url>https://aclanthology.org/P19-1279</url> </location> <part> <date>2019-07</date> <extent unit="page"> <start>2895</start> <end>2905</end> </extent> </part></mods></modsCollection>
Download as File
%0 Conference Proceedings%T Matching the Blanks: Distributional Similarity for Relation Learning%A Baldini Soares, Livio%A FitzGerald, Nicholas%A Ling, Jeffrey%A Kwiatkowski, Tom%Y Korhonen, Anna%Y Traum, David%Y Màrquez, Lluís%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics%D 2019%8 July%I Association for Computational Linguistics%C Florence, Italy%F baldini-soares-etal-2019-matching%X General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task’s training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED%R 10.18653/v1/P19-1279%U https://aclanthology.org/P19-1279%U https://doi.org/10.18653/v1/P19-1279%P 2895-2905
Download as File
Markdown (Informal)
[Matching the Blanks: Distributional Similarity for Relation Learning](https://aclanthology.org/P19-1279) (Baldini Soares et al., ACL 2019)
- Matching the Blanks: Distributional Similarity for Relation Learning (Baldini Soares et al., ACL 2019)
ACL
- Livio Baldini Soares, Nicholas FitzGerald, Jeffrey Ling, and Tom Kwiatkowski. 2019. Matching the Blanks: Distributional Similarity for Relation Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2895–2905, Florence, Italy. Association for Computational Linguistics.