PSDVec: A toolbox for incremental and scalable word embedding

• Main Authors: Li, Shaohua, Zhu, Jun, Miao, Chunyan
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2017
• Subjects: Word embedding; Matrix factorization
• Online Access: https://hdl.handle.net/10356/83166; http://hdl.handle.net/10220/42454
• Institution: Nanyang Technological University

PSDVec is a Python/Perl toolbox that learns word embeddings, i.e. the mapping of words in a natural language to continuous vectors which encode the semantic/syntactic regularities between the words. PSDVec implements a word embedding learning method based on a weighted low-rank positive semidefinite approximation. To scale up the learning process, we implement a blockwise online learning algorithm to learn the embeddings incrementally. This strategy greatly reduces the learning time of word embeddings on a large vocabulary, and can learn the embeddings of new words without re-learning the whole vocabulary. On 9 word similarity/analogy benchmark sets and 2 Natural Language Processing (NLP) tasks, PSDVec produces embeddings that has the best average performance among popular word embedding tools. PSDVec provides a new option for NLP practitioners.