Jirka Hana
Main Research Interests
- Resource light morphology and tagging; computational linguistics in general.
- Mathematical models of grammar, especially of complex word-order.
- Learner corpora.
Teaching
- Winter: NPFL063 Introduction to Linguistics
- Summer: NPFL141 Linguistics (formerly NPFL106 Linguistics), NPFL128 Practical NLP
- All my courses
Selected Bibliography
- Google Scholar
- ORCID: 0000-0001-9863-6880
- Scopus ID: 14027016000
- Researcher ID: A-9365-2008
- Rosen, Hana, Štindlová, Feldman (2013). Evaluating and automating the annotation of a learner corpus.
- Hana and Feldman (2012). Resource-Light Approaches to Computational Morphology Part 1: Monolingual Approaches
- Feldman and Hana (2010). A resource-light approach to morpho-syntactic tagging.
- Hana (2007). Czech Clitics in Higher Order Grammar. PhD Thesis
- Hana et al (2006): Tagging Portuguese with a Spanish Tagger Using Cognates.
See http://ufal.mff.cuni.cz/~hana/bib.html for the full list, including bibtex and pdfs.
Advising
- Radoslav Klíč: MSc 2011. Acquisition of inflectional paradigms with minimal supervision
- Srdjan Prodanovic: MSc 2011. Semantic disambiguation using Distributional Semantics
- Adrián Lachata: BSc 2014. Automatic assignment of diagnosis to medical reports (in Slovak)
- Ludmila Tydlitátová: BSc 2016. Native Language Identification of L2 Speakers of Czech. [pdf]
- Jan Knížek: BSc 2019. Comparison of approaches to text classification
- Petr Laitoch: MSc 2020. Text classification with limited training data
- Dan Raffl: BSc 2022. Natural Language Generation system writing football articles
- Evgeniya Ustinova: MSc 2023. Automatic detection and attribution of quotes
- Daragh Meehan: MSc 2024. Learning Multiple Languages Through Parallel Audiovisual Input
Tools
- feat - Flexible Error Annotation Tool; an environment for layered error annotation of learners corpora.
- law (feat-morph) - a tool for manual morphological disambiguation
- Russian positional tagset