TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Semantic Similarity	SICK	combine-skip (Kiros et al., 2015)	MSE	0.2687	# 2
Semantic Similarity	SICK	combine-skip (Kiros et al., 2015)	Pearson Correlation	0.8584	# 2
Semantic Similarity	SICK	combine-skip (Kiros et al., 2015)	Spearman Correlation	0.7916	# 3

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/skip-thought-vectors/semantic-similarity-on-sick)](https://paperswithcode.com/sota/semantic-similarity-on-sick?p=skip-thought-vectors)`

Skip-Thought Vectors

NeurIPS 2015 · Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard S. Zemel, Antonio Torralba, Raquel Urtasun, Sanja Fidler ·

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.