Constructing High Precision Knowledge Bases with Subjective and Factual Attributes

Autor: Kobren, Ari, Barrio, Pablo, Yakhnenko, Oksana, Hibschman, Johann, Langmore, Ian

Knowledge bases (KBs) are the backbone of many ubiquitous applications and are thus required to exhibit high precision. However, for KBs that store subjective attributes of entities, e.g., whether a movie is "kid friendly", simply estimating precisio

Externí odkaz: http://arxiv.org/abs/1905.12807

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction

Autor: Weston, Jason, Bordes, Antoine, Yakhnenko, Oksana, Usunier, Nicolas

This paper proposes a novel approach for relation extraction from free text which is trained to jointly use information from the text and from existing knowledge. Our model is based on two scoring functions that operate by learning low-dimensional em

Externí odkaz: http://arxiv.org/abs/1307.7973

Translating Embeddings for Modeling Multi-relational Data

Autor: Bordes, Antoine, Usunier, Nicolas, Garcia-Duran, Alberto, Weston, Jason, Yakhnenko, Oksana

Publikováno v: Neural Information Processing Systems (NIPS)
Neural Information Processing Systems (NIPS), Dec 2013, South Lake Tahoe, United States. pp.1-9

International audience; We consider the problem of embedding entities and relationships of multi- relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of par

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::2461c9ea4daa3fc779512f391942198c
https://hal.archives-ouvertes.fr/hal-00920777

Annotating images and image objects using a hierarchical dirichlet process model.

Autor: Yakhnenko, Oksana, Honavar, Vasant

Publikováno v: Proceedings of the 9th International Workshop: Multimedia Data Mining; 8/24/2008, p1-7, 7p