Abstract | ||
---|---|---|
•We introduce semantic frame learning framework for natural language understanding.•We introduce neural architecture for learning vector representation of semantic frame.•Considering distance and task loss together shows best representation learning performance.•Vector semantic representation invoke many useful applications around NLU including sentence search, visualization, and re-ranking. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.csl.2018.12.008 | Computer Speech & Language |
Keywords | Field | DocType |
Natural language understanding,Semantic frame learning,Deep learning,Distributed representation,Semantic vector,Semantic Corpus Visualization | Semantic memory,Vector space,Embedding,Semantic search,Computer science,Visualization,Natural language understanding,Artificial intelligence,Natural language processing,Word2vec,Machine learning | Journal |
Volume | ISSN | Citations |
56 | 0885-2308 | 1 |
PageRank | References | Authors |
0.37 | 17 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sangkeun Jung | 1 | 197 | 15.23 |