Lucie Poláková Lucie Mladová

office
423
email
polakova@ufal.mff.cuni.cz
phone
+420 951 554 254

Main Research Interests

  • discourse structure, coherence and coreference, discourse connectives
  • dependency syntax
  • information structure
  • corpus linguistics
  • machine translation evaluation
  • LLM evaluation

Projects

EdUKate - Promoting digital education of foreign-language children through machine translation

OpenEuroLLM - Developing a series of foundation models for transparent AI in Europe

SEEM-CZ -  Epistemic and Evidential Markers in Czech

u4u -  Charles translator for Ukraine

Analyzing Discourse Structure

The Prague Dependency Treebank (50k Czech sentences) is being continuously enriched with annotation of phenomena "beyond the sentence boundary". The recent version from 2024 is publicly available as Prague Dependency Treebank - Consolidated 2.0.

Past Projects (Selection)

Global Coherence - Description of global text coherence in Czech (primarily Rhetorical Structure Theory)

RapiDisc - Methods for rapid discourse annotation in selected corpora

CzeDLex - Lexicon of Czech discourse connectives, documentation here

CzeDParse - development of a shallow discourse parser for Czech

AnaConn - Anaphoricity in Connectives

KONTAKT - Cooperation Programme with University of Pennsylvania

TextLink - Structuring Discourse in Multilingual Europe

LINDAT/CLARIN - Digital Research Infrastructure for the Language Technologies, Arts and Humanities

PCEDT 2.0: Parallel English-Czech Treebank (manual translations of Penn Treebank WSJ texts); Tectogrammatical Representation of English: PEDT 1.0

Curriculum Vitae

  • 2015: Ph.D. in Mathematical Linguistics at the Faculty of Mathematics and Physics, Charles University in Prague. Ph.D. thesis: Discourse Relations in Czech, advisor: prof. PhDr. Eva Hajičová, DrSc.
  • 2008: Mgr. in Czech and German Philology at the Faculty of Philosophy and Arts, Charles University in Prague
    Master's thesis on Discourse Relations in Czech and their Representation in an Annotated Corpus of Texts (in Czech; pdf), advisor: Prof. PhDr. Eva Hajičová, DrSc.

Teaching

Synsémantika (FF UK, ABO700328): https://is.cuni.cz/studium/predmety/index.php?do=predmet&kod=ABO700328

Analýza diskurzu (FF UK, ABO700706): https://is.cuni.cz/studium/predmety/index.php?do=predmet&kod=ABO700706

Selected Bibliography