(2015. 6) Skip Thought

• published in 2015. 6

• Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard S. Zemel, Antonio Torralba, Raquel Urtasun and Sanja Fidler

Simple summary

• Approach for unsupervised learning of a generic, distributed sentence encoder.

• skip-thought word2vec model to the sentence level, training auto-encoders that predict the previous and next sentences.

• Sentences that share semantic and syntactic properties are thus mapped

  to similar vector representations.

images