To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Character-Level Convoluti… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Character-Level Convolutional Neural Network for Paraphrase Detection and Other Experiments

Conference paper
Authors Vladislav Maraev
Chakaveh Saedi
João Rodrigues
António Branco
João Silva
Published in Artificial Intelligence and Natural Language: 6th Conference, AINL 2017, St. Petersburg, Russia, September 20--23, 2017, Revised Selected Papers
ISBN 978-3-319-71746-3
Publisher Springer International Publishing
Place of publication Cham
Publication year 2017
Published at
Language en
Subject categories Computational linguistics


The central goal of this paper is to report on the results of an experimental study on the application of character-level embeddings and basic convolutional neural network to the shared task of sentence paraphrase detection in Russian. This approach was tested in the standard run of Task 2 of that shared task and revealed competitive results, namely 73.9% accuracy against the test set. It is compared against a word-level convolutional neural network for the same task, and varied other approaches, such as rule-based and classical machine learning.

Page Manager: Webmaster|Last update: 9/11/2012

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?