TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Skip-Thought Vectors

Skip-Thought Vectors

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

2015-06-22NeurIPS 2015 12
PaperPDFCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCode

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.

Results

TaskDatasetMetricValueModel
Language ModellingSICKMSE0.2687combine-skip (Kiros et al., 2015)
Language ModellingSICKPearson Correlation0.8584combine-skip (Kiros et al., 2015)
Language ModellingSICKSpearman Correlation0.7916combine-skip (Kiros et al., 2015)
Sentence Pair ModelingSICKMSE0.2687combine-skip (Kiros et al., 2015)
Sentence Pair ModelingSICKPearson Correlation0.8584combine-skip (Kiros et al., 2015)
Sentence Pair ModelingSICKSpearman Correlation0.7916combine-skip (Kiros et al., 2015)
Semantic SimilaritySICKMSE0.2687combine-skip (Kiros et al., 2015)
Semantic SimilaritySICKPearson Correlation0.8584combine-skip (Kiros et al., 2015)
Semantic SimilaritySICKSpearman Correlation0.7916combine-skip (Kiros et al., 2015)