Mapping distributional semantics to property norms with deep neural networks
Word embeddings have been very successful in many natural language processing tasks, but they characterize the meaning of a word/concept by uninterpretable “context signatures”. Such a representation can render results obtained using embeddings difficult to interpret. Neighboring word vectors may ha...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019
|
Subjects: | |
Online Access: | View Fulltext in Publisher |