Injecting Logical Background Knowledge into Embeddings for Relation Extraction
Tim Rocktaschel, Sameer Singh, Sebastian Riedel

Citation
Tim Rocktaschel, Sameer Singh, Sebastian Riedel. "Injecting Logical Background Knowledge into Embeddings for Relation Extraction". North American Association of Computational Linguistics (NAACL), 31, May, 2015.

Abstract
Matrix factorization approaches to relation extraction provide several attractive features: they support distant supervision, handle open schemas, and leverage unlabeled data. How- ever, such methods share a shortcoming with all other distantly supervised approaches: they cannot learn to extract target relations with- out existing data in the knowledge base, and likewise, these models are inaccurate for rela- tions with sparse data. Rule-based extractors, on the other hand, can be easily extended to novel relations, and improved for existing but inaccurate relations, through first-order formulae that capture auxiliary domain knowledge. However, usually a large set of such formulae is necessary to achieve generalization. In this paper, we introduce a paradigm for learning low-dimensional embeddings of entity-pairs and relations that combine the advantages of matrix factorization with first-order logic domain knowledge. We introduce simple approaches for estimating such embeddings, as well as a novel training algorithm to jointly optimize over factual and first-order logic in- formation. Our results show that this method is able to learn accurate extractors with little or no distant supervision alignments, while at the same time generalizing to textual patterns that do not appear in the formulae.

Electronic downloads

Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Tim Rocktaschel, Sameer Singh, Sebastian Riedel. <a
  href="http://www.terraswarm.org/pubs/496.html"
  >Injecting Logical Background Knowledge into Embeddings
  for Relation Extraction</a>, North American
  Association of Computational Linguistics (NAACL), 31, May,
  2015.

• Plain text

  Tim Rocktaschel, Sameer Singh, Sebastian Riedel.
  "Injecting Logical Background Knowledge into Embeddings
  for Relation Extraction". North American Association of
  Computational Linguistics (NAACL), 31, May, 2015.

• BibTeX

  @inproceedings{RocktaschelSinghRiedel15_InjectingLogicalBackgroundKnowledgeIntoEmbeddingsFor,
      author = {Tim Rocktaschel and Sameer Singh and Sebastian
                Riedel},
      title = {Injecting Logical Background Knowledge into
                Embeddings for Relation Extraction},
      booktitle = {North American Association of Computational
                Linguistics (NAACL)},
      day = {31},
      month = {May},
      year = {2015},
      abstract = {Matrix factorization approaches to relation
                extraction provide several attractive features:
                they support distant supervision, handle open
                schemas, and leverage unlabeled data. How- ever,
                such methods share a shortcoming with all other
                distantly supervised approaches: they cannot learn
                to extract target relations with- out existing
                data in the knowledge base, and likewise, these
                models are inaccurate for rela- tions with sparse
                data. Rule-based extractors, on the other hand,
                can be easily extended to novel relations, and
                improved for existing but inaccurate relations,
                through first-order formulae that capture
                auxiliary domain knowledge. However, usually a
                large set of such formulae is necessary to achieve
                generalization. In this paper, we introduce a
                paradigm for learning low-dimensional embeddings
                of entity-pairs and relations that combine the
                advantages of matrix factorization with
                first-order logic domain knowledge. We introduce
                simple approaches for estimating such embeddings,
                as well as a novel training algorithm to jointly
                optimize over factual and first-order logic in-
                formation. Our results show that this method is
                able to learn accurate extractors with little or
                no distant supervision alignments, while at the
                same time generalizing to textual patterns that do
                not appear in the formulae.},
      URL = {http://terraswarm.org/pubs/496.html}
  }
  

Posted by Carlos Guestrin on 9 Feb 2015.
Groups: services