Automatic text simplification of Russian texts using control tokens

Anna Dmitrieva


Abstract
This paper describes the research on the possibilities to control automatic text simplification with special tokens that allow modifying the length, paraphrasing degree, syntactic complexity, and the CEFR (Common European Framework of Reference) grade level of the output texts, i.e. the level of language proficiency a non-native speaker would need to understand them. The project is focused on Russian texts and aims to continue and broaden the existing research on controlled Russian text simplification. It is done by exploring available datasets for monolingual Russian machine translation (paraphrasing and simplification), experimenting with various model architectures, and adding control tokens that have not been used on Russian texts previously.
Anthology ID:
2023.bsnlp-1.9
Volume:
Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Jakub Piskorski, Michał Marcińczuk, Preslav Nakov, Maciej Ogrodniczuk, Senja Pollak, Pavel Přibáň, Piotr Rybak, Josef Steinberger, Roman Yangarber
Venue:
BSNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
70–77
Language:
URL:
https://aclanthology.org/2023.bsnlp-1.9
DOI:
10.18653/v1/2023.bsnlp-1.9
Bibkey:
Cite (ACL):
Anna Dmitrieva. 2023. Automatic text simplification of Russian texts using control tokens. In Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pages 70–77, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Automatic text simplification of Russian texts using control tokens (Dmitrieva, BSNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.bsnlp-1.9.pdf
Video:
 https://aclanthology.org/2023.bsnlp-1.9.mp4