Matching the Blanks: Distributional Similarity for Relation Learning

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
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://vimeo.com/384767351
Code
 additional community code
Data
FewRelSemEval-2010 Task 8TACRED