Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction
作者： Nicolas Usunier , Jason Weston , Antoine Bordes , Oksana Yakhnenko
DOI:
关键词: Knowledge base 、 Artificial intelligence 、 Natural language processing 、 Embedding 、 Relationship extraction 、 Computer science
摘要: This paper proposes a novel approach for relation extraction from free text which is trained to jointly use information the and existing knowledge. Our model based on scoring functions that operate by learning low-dimensional embeddings of words, entities relationships knowledge base. We empirically show New York Times articles aligned with Freebase relations our able efficiently extra provided large subset data (4M entities, 23k relationships) improve over methods rely features alone.
arxiv.org
aclweb.org
archives-ouvertes.fr
researchgate.net 参考文章(22)
Mihai Surdeanu, Ramesh Nallapati, Julie Tibshirani, Christopher D. Manning, Multi-instance Multi-label Learning for Relation Extraction empirical methods in natural language processing. pp. 455- 465 ,(2012)
Volker Tresp, Hans-peter Kriegel, Maximilian Nickel, A Three-Way Model for Collective Learning on Multi-Relational Data international conference on machine learning. pp. 809- 816 ,(2011)
Michael J. Cafarella, Oren Etzioni, Stephen Soderland, Michele Banko, Matt Broadhead, Open information extraction from the web international joint conference on artificial intelligence. pp. 2670- 2676 ,(2007)
Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam Hruschka, Tom Mitchell, None, Toward an architecture for never-ending language learning national conference on artificial intelligence. pp. 1306- 1313 ,(2010)
Yoshua Bengio, Xavier Glorot, Jason Weston, Antoine Bordes, Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing international conference on artificial intelligence and statistics. ,vol. 22, pp. 127- 135 ,(2012)
Sebastian Riedel, Limin Yao, Andrew McCallum, Modeling relations and their mentions without labeled text european conference on machine learning. pp. 148- 163 ,(2010) , 10.1007/978-3-642-15939-8_10
Benjamin M. Marlin, Sebastian Riedel, Andrew McCallum, Limin Yao, Relation Extraction with Matrix Factorization and Universal Schemas north american chapter of the association for computational linguistics. pp. 74- 84 ,(2013)
Cynthia Matuszek, Luke Zettlemoyer, Dieter Fox, Liefeng Bo, Nicholas Fitzgerald, A Joint Model of Language and Perception for Grounded Attribute Learning international conference on machine learning. pp. 1435- 1442 ,(2012) , 10.13016/M2EHU6-1M90
Amarnag Subramanya, William W. Cohen, Ni Lao, Fernando Pereira, Reading The Web with Learned Syntactic-Semantic Inference Rules empirical methods in natural language processing. pp. 1017- 1026 ,(2012)
Mark Craven, Johan Kumlien, Constructing Biological Knowledge Bases by Extracting Information from Text Sources intelligent systems in molecular biology. pp. 77- 86 ,(1999)