Neural word embeddings with multiplicative feature interactions for tensor-based compositions.
Joo-Kyung KimMarie-Catherine de MarneffeEric Fosler-LussierPublished in: VS@HLT-NAACL (2015)
Keyphrases
- feature interactions
- network architecture
- co occurrence
- high order
- vector space
- neural network
- n gram
- low dimensional
- bio inspired
- manifold learning
- keywords
- data sets
- word sense disambiguation
- dimensionality reduction
- associative memory
- euclidean space
- feature vectors
- subspace learning
- word recognition
- text corpus
- nonlinear predictive control