Abstract | ||
---|---|---|
Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Artificial Intelligence | Embedding,Information retrieval,Computer science,Semantic Web,Artificial intelligence,Knowledge base,Artificial neural network,Strengths and weaknesses,Machine learning |
DocType | Volume | Citations |
Journal | abs/1806.09504 | 0 |
PageRank | References | Authors |
0.34 | 24 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arthur Colombini Gusmão | 1 | 0 | 0.34 |
Alvaro Henrique Chaim Correia | 2 | 0 | 1.35 |
Glauber de Bona | 3 | 31 | 6.59 |
Fábio Cozman | 4 | 18 | 10.16 |