Capturing and evaluating higher order relations in word embeddings using tensor factorization

Bailey, Eric.

2017

Description
  • Abstract: In Natural Language Processing, most popular word embeddings involve low-rank factorization of a word co-occurrence based matrix. We aim to generalize this trend by studying word embeddings given by low-rank factorization of word co-occurrence based higher-order arrays, or tensors. We present four novel word embeddings based on tensor factorization and show they outperform popular state-... read more
This object is in collection Corporate name Permanent URL
ID:
qz20t4633
To Cite:
DCA Citation Guide    EndNote