Binary Paragraph Vectors

Karol Grzegorczyk, Marcin Kurdziel

Nov 04, 2016 (modified: Jan 17, 2017) ICLR 2017 conference submission readers: everyone
  • Abstract: Recently Le & Mikolov described two log-linear models, called Paragraph Vector, that can be used to learn state-of-the-art distributed representations of documents. Inspired by this work, we present Binary Paragraph Vector models: simple neural networks that learn short binary codes for fast information retrieval. We show that binary paragraph vectors outperform autoencoder-based binary codes, despite using fewer bits. We also evaluate their precision in transfer learning settings, where binary codes are inferred for documents unrelated to the training corpus. Results from these experiments indicate that binary paragraph vectors can capture semantics relevant for various domain-specific documents. Finally, we present a model that simultaneously learns short binary codes and longer, real-valued representations. This model can be used to rapidly retrieve a short list of highly relevant documents from a large document collection.
  • TL;DR: Learning short codes for text documents with Binary Paragraph Vectors.
  • Conflicts: agh.edu.pl
  • Keywords: Natural language processing, Transfer Learning

Loading