Tomas Mikolov

Researcher at Google specializing in efficient neural network architectures for natural language processing. Pioneered scalable approaches to computing word representations and has made significant contributions to language modeling and neural machine translation.

Sources in this wiki

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality

Topics

• Word Embeddings, Language Models

Notes

Primary author of the influential Word2Vec paper introducing CBOW and Skip-gram architectures. His work on efficient neural network training for NLP has been foundational to the field.