Towards Automatic Finnish Text Simplification

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Automatic text simplification (ATS/TS) models typically require substantial parallel training data. This paper describes our work on expanding the Finnish-Easy Finnish parallel corpus and making baseline simplification models. We discuss different approaches to document and sentence alignment. After finding the optimal alignment methodologies, we increase the amount of document-aligned data 6.5 times and add a sentence-aligned version of the dataset consisting of more than twelve thousand sentence pairs. Using sentence-aligned data, we fine-tune two models for text simplification. The first is mBART, a sequence-to-sequence denoising auto-encoder proven to show good results for monolingual translation tasks. The second is the Finnish GPT model, for which we utilize instruction fine-tuning. This work is the first attempt to create simplification models for Finnish using monolingual parallel data in this language. The data has been deposited in the Finnish Language Bank (Kielipankki) and is available for non-commercial use, and the models are accessible through Huggingface.
Original languageEnglish
Title of host publicationProceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024
EditorsGiorgio Maria Di Nunzio, Federica Vezzani, Liana Ermakova, Hosein Azarbonyad, Jaap Kamps
Number of pages12
Place of PublicationParis
PublisherEuropean Language Resources Association (ELRA)
Publication dateMay 2024
ISBN (Electronic)978-2-493814-15-9
Publication statusPublished - May 2024
MoE publication typeA4 Article in conference proceedings
EventDeTermIt! Evaluating Text Difficulty in a Multilingual Context - Turin, Italy
Duration: 21 May 202421 May 2024

Publication series

NameInternational conference on computational linguistics
PublisherInternational Committee on Computational Linguistics
ISSN (Print)2951-2093
NameLREC proceedings
PublisherLanguage Resources Association (ELRA)
ISSN (Electronic)2522-2686

Fields of Science

  • 6121 Languages
  • 113 Computer and information sciences

Cite this