Main Research Interests
- Automatic post-editing of Machine translation
- Dependency parsing
- Unsupervised and semi-supervised methods
- Machine translation
Visit my Research MicroBlog to see what I am currently up to!
Discovering the structure of natural language sentences by unsupervised and semi-supervised methods
(Odhalování struktury vět přirozeného jazyka pomocí neřízených a částečně řízených metod)
This is my topic for PhD studies (and my dissertation). I am only starting my work on the topic. However, my work on HamleDT is also part of my studies, as it is related to the topic.
I am a member of HamleDT, which is a project of harmonizing dependency treebanks for various languages.
Currently, my main project is QTLeap, a project aimed at significantly improving the quality of machine translation using deep language processing approaches.
I am also currently employed on the Khresmoi project, focusing of machine translation of medical texts for information retrieval (translation of search queries and resulting snippets).
MSTperl is a reimplementation of the Maximum spanning tree dependency parser (McDonald et al., 2005) in Perl. It is tuned for Czech and has several advanced features that are useful for parsing the machine-translated sentences by Depfix.
My Erdös number is ≤ 7 (me - Jan Hajič - Jason Eisner - Jean-Marc Champarnaud - Gérard Duchamp - Jean-Yves Thibon - Persi Diaconis - Paul Erdös)