Paper Info
Title
Deep learning of knowledge graph embeddings for semantic parsing of Twitter dialogs
Abstract
This paper presents a novel method to learn neural knowledge graph embeddings. The embeddings are used to compute semantic relatedness in a coherence-based semantic parser. The approach learns embeddings directly from structured knowledge representations. A deep neural network approach known as Deep Structured Semantic Modeling (DSSM) is used to scale the approach to learn neural embeddings for all of the concepts (pages) of Wikipedia. Experiments on Twitter dialogs show a 23.6% reduction in semantic parsing errors compared to the state-of-the-art unsupervised approach.
Year
DOI
Venue
2014
10.1109/GlobalSIP.2014.7032187
Signal and Information Processing
Keywords
Field
DocType
learning (artificial intelligence),natural language processing,neural nets,social networking (online),DSSM approach,Twitter dialogs,Wikipedia,coherence-based semantic parser,deep learning,deep neural network approach,deep structured semantic modeling,neural embedding learning,neural knowledge graph embeddings,semantic parsing,semantic parsing error reduction,semantic relatedness,Twitter,deep learning,dialog,semantic parsing
Semantic similarity,Semantic Web Stack,Computer science,Encyclopedia,Artificial intelligence,Natural language processing,Parsing,Deep learning,Artificial neural network,Semantic computing,Semantics
Conference
Citations 
PageRank 
References 
8
0.48
22
Authors
2
Name
Order
Citations
PageRank
Larry P. Heck11096100.58
Hongzhao Huang21266.64