Year: 2017
Type: conference-paper
Abstract: Recently Le & Mikolov described two log-linear models, called Paragraph Vector, that can be used to learn state-ofthe-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 domainspecific 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.
DOI: 10.18653/v1/w17-2615
Authors: Karol Grzegorczyk, Marcin Kurdziel
Institution: AGH University of Krakow
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2547912976