UMR CNRS 7253

Everest
Everest
Everest
Everest
Everest

Site Tools


en:2and3ways

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
en:2and3ways [d/m/Y H:i]
bordesan
en:2and3ways [d/m/Y H:i]
bordesan
Line 1: Line 1:
-====== Project: ​Translating ​Embeddings for Modeling Multi-relational Data ======+====== Project: ​Combining Two And Three-Way ​Embeddings ​Models ​for Link Prediction in Knowledge Bases ======
  
 +Abstract: This paper tackles the problem of endogenous link prediction for Knowledge Base completion. Knowledge Bases can be represented as directed graphs whose nodes correspond to entities and edges to relationships. Previous attempts either consist of powerful systems with high capacity to model complex connectivity patterns, which unfortunately usually end up overfitting on rare relationships,​ or in approaches that trade capacity for simplicity in order to fairly model all relationships,​ frequent or not. In this paper, we propose Tatec a happy medium obtained by complementing a high-capacity model with a simpler one, both pre-trained separately and then combined. We present several variants of this model with different kinds of regularization and combination strategies and show that this approach outperforms existing methods on different types of relationships by achieving state-of-the-art results on four benchmarks of the literature.
  
 +===== Paper =====
 +
 +  * Paper is on {{http://​arxiv.org/​abs/​1506.00999 | (arxiv}}}
 ===== Data ===== ===== Data =====
  
   * **Family database **. cPickle format: {{:​en:​family.tgz| ​ (data)}}. See [1] for more details.   * **Family database **. cPickle format: {{:​en:​family.tgz| ​ (data)}}. See [1] for more details.
- 
- 
-===== Contacts ===== 
  
 ===== References ===== ===== References =====
-[1] A. Bordes, N. Usunier, A. Garcia-DuranJWeston ​and OYakhnenkoTranslating ​Embeddings for Modeling Multi-relational DataIn Advances of Neural Information Processing Systems 2013. \\+[1] A. Garcia-Duarn, A. BordesNUsunier ​and YGrandvaletCombining Two And Three-Way ​Embeddings ​Models ​for Link Prediction in Knowledge Bases. arxiv.org/​abs/​1506.009992015. \\