Hi, I am Pavel Sofroniev

This is my personal website where you can find my ongoing projects as well as the publications I have contributed to.


filmadder is a privacy-conscious group-oriented website and app for finding and organising films. It is an open source project developed by Stela ♡ and me. Still in alpha, but already lovingly used by our close friends.

Shemetna Varna is a non-profit urban race in which teams of 4 aim to complete about a dozen tasks located throughout the centre of my home town Varna. It takes place annually, attracting more than 200 participants last year. I am part of the organising team of volunteers since the first competition in 2011.

Глагол (transliterated Glagol) is a small association of people interested in the contemporary evolution of the Bulgarian language. I am one of the association's two co-founders and the main developer and maintainer of its website.


Taraka Rama, Johannes Wahle, Pavel Sofroniev and Gerhard Jäger (WIP), Fast and unsupervised methods for multilingual cognate clustering. [pdf] [code] [bib]
Kuan Yu, Pavel Sofroniev, Erik Schill and Erhard Hinrichs (2017), The parse is darc and full of errors: Universal dependency parsing with transition-based and graph-based algorithms. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 126-133 [pdf] [code] [bib]
Taraka Rama, Çağrı Çöltekin and Pavel Sofroniev (2017), Computational analysis of Gondi dialects. In Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), pages 26-35 [pdf] [bib]
Gerhard Jäger, Johann-Mattis List and Pavel Sofroniev (2017), Using support vector machines and state-of-the-art algorithms for phonetic alignment to identify cognates in multi-lingual wordlists. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, volume 1, pages 1205-1216 [pdf] [www] [code] [bib]
Gerhard Jäger and Pavel Sofroniev (2016), Automatic cognate classification with a Support Vector Machine. In Proceedings of the 13th Conference on Natural Language Processing, pages 128-134 [pdf] [bib]