Skip-Thought Vectors

Code

• github.com/facebookresearch/InferSent
  pytorch★ 2,280
• github.com/soskek/bookcorpus
  none★ 852
• github.com/dashayushman/TAC-GAN
  tf★ 105
• github.com/kushalpatil1997/text_to_image_synthesis
  tf★ 2
• github.com/dwright37/phylogenetic-autoencoder
  tf★ 0
• github.com/thomasyue/tf2-skip-thoughts
  tf★ 0
• github.com/whitneysattler/Skip-Thoughts
  none★ 0
• github.com/luweizhang/joint_embeddings
  pytorch★ 0
• github.com/arukavina/baking-lyrics
  tf★ 0
• github.com/ryankiros/skip-thoughts
  none★ 0

Abstract

We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets. The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice. We will make our encoder publicly available.

Tasks

Benchmark Results

Reproductions