Capturing and evaluating higher order relations in word embeddings using tensor factorizationBailey, Eric.
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
- Tufts University. Department of Computer Science.
- Permanent URL
|To Cite:||DCA Citation Guide|