research
∙
12/15/2019
Multilingual is not enough: BERT for Finnish
Deep learning-based language models pretrained on large unannotated text...
share
research
∙
10/09/2019
Is Multilingual BERT Fluent in Language Generation?
The multilingual BERT model is trained on 104 languages and meant to ser...
research
∙
10/04/2019
Template-free Data-to-Text Generation of Finnish Sports News
News articles such as sports game reports are often thought to closely f...
research
∙
06/26/2019
Leveraging Text Repetitions and Denoising Autoencoders in OCR Post-correction
A common approach for improving OCR quality is a post-processing step ba...
research
∙
02/03/2019
Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks
In this paper we present a novel lemmatization method based on a sequenc...
research
∙
11/28/2011