# 文件:Probabilistic Belief Embedding for Large-scale Knowledge Population.pdf

Probabilistic_Belief_Embedding_for_Large-scale_Knowledge_Population.pdf(file size: 946 KB, MIME type: application/pdf)

This paper contributes a novel embedding model which measures the probability of each belief $\langle h,r,t,m\rangle$ in a large-scale knowledge repository via simultaneously learning distributed representations for entities ($h$ and $t$), relations ($r$), and the words in relation mentions ($m$). It facilitates knowledge population by means of simple vector operations to discover new beliefs. Given an imperfect belief, we can not only infer the missing entities, predict the unknown relations, but also tell the plausibility of the belief, just leveraging the learnt embeddings of remaining evidences. To demonstrate the scalability and the effectiveness of our model, we conduct experiments on several large-scale repositories which contain millions of beliefs from WordNet, Freebase and NELL, and compare it with other cutting-edge approaches via competing the performances assessed by the tasks of {\it entity inference}, {\it relation prediction} and {\it triplet classification} with their respective metrics. Extensive experimental results show that the proposed model outperforms the state-of-the-arts with significant improvements.

## File history

Click on a date/time to view the file as it appeared at that time.

 Date/Time Dimensions User Comment current 14:26, 8 August 2016 (946 KB) Fanmiao (Talk | contribs) 16:27, 22 May 2015 (463 KB) Fanmiao (Talk | contribs) 23:18, 20 May 2015 (463 KB) Fanmiao (Talk | contribs) 02:09, 18 May 2015 (461 KB) Fanmiao (Talk | contribs) 00:34, 18 May 2015 (461 KB) Fanmiao (Talk | contribs) 17:20, 17 May 2015 (461 KB) Fanmiao (Talk | contribs) 17:02, 14 May 2015 (456 KB) Fanmiao (Talk | contribs) 01:48, 13 May 2015 (456 KB) Fanmiao (Talk | contribs) This paper contributes a novel embedding model which measures the probability of each belief $\langle h,r,t,m\rangle$ in a large-scale knowledge repository via simultaneously learning distributed representations for entities ($h$ and $t$), relations (\$...
• You cannot overwrite this file.

The following file is a duplicate of this file (more details):

The following page links to this file: