Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings

arXiv:2104.08928v3 Announce Type: replace-cross
Abstract: Unstructured text provides decision-makers with a rich data source in many domains, ranging from product reviews in retail to nursing notes in healthcare. To leverage this information, words are typically translated into word embeddings -- vectors that encode the semantic relationships between words -- through unsupervised learning algorithms such as matrix factorization. However, learning word embeddings from new domains with limited training data can be challenging, because the meaning/usage may be different in the new …

abstract arxiv cs.cl cs.lg data decision domains embeddings encode factorization healthcare information makers matrix notes nursing product product reviews relationships retail reviews rich data semantic stat.ml text through transfer transfer learning translated type unstructured unsupervised vectors word word embeddings words