Science

So far, I have been working in the field of Computational Linguistics / Natural Language Processing, which combines my primary field of expertise (computer science) with one of my main hobbyist interests (linguistics and languages). The topics I am especially interested in include:

• probabilistic models of grammatical structures and their application in unsupervised learning and modeling human language acquisition,
• grammar theories treating words as basic units of language (Whole Word Morphology, dependency grammars),
• string similarity, string transformations and finite-state technology,
• applications of language technology in humanities and social sciences.

Given good research opportunities, I am open to other topics as well.

PhD thesis

• Maciej Janicki:
  Statistical and Computational Models for Whole Word Morphology.
  PhD thesis, University of Leipzig, 2019. pdf

Conference Papers

• Maciej Janicki:
  Finite State Transducer Calculus for Whole Word Morphology.
  Proceedings of the 14th International Conference on Finite-State Methods and Natural Language Processing (FSMNLP), Dresden, Germany, September 2019. pdf
• Maciej Janicki:
  Semi-Supervised Induction of POS-Tag Lexicons with Tree Models.
  Proceedings of RANLP 2019, Varna, Bulgaria, September 2019. pdf
• Lydia Müller, Uwe Quasthoff and Maciej Sumalvico:
  Corpora of Typical Sentences.
  In: LREC 2018, Eleventh International Conference on Language Resources and Evaluation, Miyazaki, Japan, 2018.
• Maciej Sumalvico:
  Unsupervised Learning of Morphology with Graph Sampling.
  In: Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2017), Varna, Bulgaria, 2017. pdf
• Dirk Goldhahn, Maciej Sumalvico and Uwe Quasthoff:
  Corpus Collection for under-resourced languages with more than one million speakers.
  In: Workshop on Collaboration and Computing for Under-Resourced Languages (CCURL), LREC, Portorož, Slovenia, 2016.
• Maciej Janicki:
  A Multi-purpose Bayesian Model for Word-Based Morphology.
  In: Systems and Frameworks for Computational Morphology – Fourth International Workshop, SFCM 2015, Springer, 2015.
• Maciej Janicki:
  Unsupervised Learning of A-Morphous Inflection with Graph Clustering.
  In: Proceedings of the RANLP 2013 Student Workshop, 2013.
• Michał Marcińczuk, Jan Kocoń and Maciej Janicki:
  Liner2–a customizable framework for proper names recognition for Polish.
  In: Intelligent Tools for Building a Scientific Information Platform, Springer Berlin Heidelberg, 2013.
• Maciej Janicki:
  A Lexeme-Clustering Algorithm for Unsupervised Learning of Morphology.
  In: Dritte Studentenkonferenz Informatik Leipzig – SKIL 2012, 2012. Best paper award.
• Michał Marcińczuk and Maciej Janicki:
  Optimizing CRF-based model for proper name recognition in Polish texts.
  In: Computational Linguistics and Intelligent Text Processing, Springer Berlin Heidelberg, 2012

(between Jan 2016 and May 2019 under the name Maciej Sumalvico)

Unpublished papers

• Maciej Janicki:
  Unsupervised Vocabulary Expansion with Whole Word Morphology.
  Rejected from both ACL and EMNLP, 2019. pdf