Name
Title | ||
|---|---|---|
Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering. |
Abstract | ||
|---|---|---|
We propose the Gaussian attention model for content-based neural memoryaccess. With the proposed attention model, a neural network has theadditional degree of freedom to control the focus of its attention froma laser sharp attention to a broad attention. It is applicable wheneverwe can assume that the distance in the latent space reflects some notionof semantics. We use the proposed attention model as a scoring functionfor the embedding of a knowledge base into a continuous vector space andthen train a model that performs question answering about the entitiesin the knowledge base. The proposed attention model can handle both thepropagation of uncertainty when following a series of relations and alsothe conjunction of conditions in a natural way. On a dataset of soccerplayers who participated in the FIFA World Cup 2014, we demonstrate thatour model can handle both path queries and conjunctive queries well. |
Year | Venue | Field |
|---|---|---|
2016 | arXiv: Machine Learning | Conjunctive query,Question answering,Embedding,Computer science,Supervised learning,Artificial intelligence,Deep learning,Knowledge base,Artificial neural network,Machine learning,Semantics |
DocType | Volume | Citations |
Journal | abs/1611.02266 | 1 |
PageRank | References | Authors |
0.35 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Liwen Zhang | 1 | 25 | 6.25 |
| John M. Winn | 2 | 5008 | 300.57 |
| Ryota Tomioka | 3 | 1367 | 91.68 |