skip-thought-vectors-kiros-2015
IN premise — summaries/2026/08/24/wiki-Sentence_embedding.md
Created 2026-08-25T02:58:54+00:00
Skip-Thought Vectors (Kiros et al., 2015) use an encoder-decoder architecture that trains sentence representations by predicting neighboring sentences in a document.
Summary
This is a foundational technique for turning sentences into numerical vectors without any human labeling. The trick is that the system learns to represent a sentence by training itself to predict what sentences come just before and after it in a document, so the "meaning" is captured implicitly through context rather than defined by a dictionary or annotation task.