Conversational Question Generation in Russian

In this paper, we discuss possibilities of automatic generation of conversational questions in Russian. We are exploring the possibility of using "A Conversational Question Answering Challenge" (CoQA) dataset translated into Russian for training an encoder-decoder model. We review several...

Full description

Saved in:
Bibliographic Details
Published in2020 27th Conference of Open Innovations Association (FRUCT) Vol. 27; no. 1; pp. 1 - 8
Main Authors Makhnytkina, Olesia, Matveev, Anton, Svischev, Aleksei, Korobova, Polina, Zubok, Dmitrii, Mamaev, Nikita, Tchirkovskii, Artem
Format Conference Proceeding Journal Article
LanguageEnglish
Published FRUCT 01.09.2020
Subjects
automatic tutoring
Computer languages
cross-lingual learning
Linguistics
Natural language processing
sonversational question generation
Task analysis
Testing
Online AccessGet full text

Cover

More Information
Summary:In this paper, we discuss possibilities of automatic generation of conversational questions in Russian. We are exploring the possibility of using "A Conversational Question Answering Challenge" (CoQA) dataset translated into Russian for training an encoder-decoder model. We review several techniques for improving the quality of questions generated in the Russian language. The results are evaluated manually. Combining a neural network-based approach with a rules-based approach, we develop a system for automatic examination of university students.
ISSN:2305-7254
2343-0737
DOI:10.23919/FRUCT49677.2020.9211056