Skip to Main content Skip to Navigation
Conference papers

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction

Abstract : This paper proposes a novel approach for rela- tion extraction from free text which is trained to jointly use information from the text and from existing knowledge. Our model is based on scoring functions that operate by learning low-dimensional embeddings of words, entities and relationships from a knowledge base. We empirically show on New York Times articles aligned with Freebase relations that our approach is able to efficiently use the extra information provided by a large subset of Freebase data (4M entities, 23k relationships) to improve over methods that rely on text features alone.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00880455
Contributor : Antoine Bordes <>
Submitted on : Wednesday, November 6, 2013 - 10:52:33 AM
Last modification on : Wednesday, July 4, 2018 - 4:44:02 PM
Long-term archiving on: : Friday, April 7, 2017 - 10:03:00 PM

File

weston13emnlp.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00880455, version 1

Collections

Citation

Jason Weston, Antoine Bordes, Oksana Yakhnenko, Nicolas Usunier. Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction. Conference on Empirical Methods in Natural Language Processing, Oct 2013, Seattle, United States. pp.1366-1371. ⟨hal-00880455⟩

Share

Metrics

Record views

264

Files downloads

700