ParaPhraser: Russian paraphrase corpus and shared task

Show full item record



Permalink

http://hdl.handle.net/10138/232301

Citation

Pivovarova , L , Pronoza , E , Yagunova , E & Pronoza , A 2017 , ParaPhraser: Russian paraphrase corpus and shared task . in A Filchenkov , L Pivovarova & J Žižka (eds) , Artificial Intelligence and Natural Language : 6th Conference, AINL 2017, St. Petersburg, Russia, September 20–23, 2017, Revised Selected Papers . Communications in Computer and Information Science , vol. 789 , Springer , Cham , pp. 211-225 , Conference on Artificial Intelligence and Natural Language , St.Petersburg , Russian Federation , 20/09/2017 . https://doi.org/10.1007/978-3-319-71746-3_18

Title: ParaPhraser: Russian paraphrase corpus and shared task
Author: Pivovarova, Lidia; Pronoza, Ekaterina; Yagunova, Elena; Pronoza, Anton
Editor: Filchenkov, Andrey; Pivovarova, Lidia; Žižka, Jan
Contributor: University of Helsinki, Department of Computer Science
Publisher: Springer
Date: 2017
Language: eng
Belongs to series: Artificial Intelligence and Natural Language 6th Conference, AINL 2017, St. Petersburg, Russia, September 20–23, 2017, Revised Selected Papers
Belongs to series: Communications in Computer and Information Science
ISBN: 978-3-319-71745-6
978-3-319-71746-3
URI: http://hdl.handle.net/10138/232301
Abstract: The paper describes the results of the First Russian Paraphrase Detection Shared Task held in St.-Petersburg, Russia, in October 2016. Research in the area of paraphrase extraction, detection and generation has been successfully developing for a long time while there has been only a recent surge of interest towards the problem in the Russian community of computational linguistics. We try to overcome this gap by introducing the project ParaPhraser.ru dedicated to the collection of Russian paraphrase corpus and organizing a Paraphrase Detection Shared Task, which uses the corpus as the training data. The participants of the task applied a wide variety of techniques to the problem of paraphrase detection, from rule-based approaches to deep learning, and results of the task reflect the following tendencies: the best scores are obtained by the strategy of using traditional classifiers combined with fine-grained linguistic features, however, complex neural networks, shallow methods and purely technical methods also demonstrate competitive results.
Subject: 6121 Languages
113 Computer and information sciences
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
AINL2017_paper_24.pdf 213.5Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record