Invited Talk: Word embeddings and their research directions Slides

Bofang Li, hosted by Guodong Jin

In recent years, there is a growing interest in word embedding models, where words are embedded into low-dimensional (dense) real-valued vectors. The trained word embeddings can be directly used for solving tasks like word similarity and word analogy, part-of-speech tagging, chunking, named entity recognition. This talk introduces the basic ideas of training word embedding models. It also discusses few directions of word embeddings based on the talker’s recent research experiences, regarding both effectiveness and efficiency.

BrainStorm: How to retrieve papars related to a certain topic

Weekly Meetup

Welcome to join our Wechat Group