Tatyana Ruzsics (Soldatova) was a member of the URPP Language and Space from 2016 to 2021.

She was a doctoral student under the supervision of Tanja Samardžić (co-supervision with Rico Sennrich) in the project Upstream Text Processing. Her research interests include deep learning methods for upstream NLP processing: writing normalization, lemmatization, morphological segmentation and morphological reinflection. She is working on the character-level neural machine translation methods that allow processing the information on multiple levels of text organization (characters, morphemes, words, sentences) in combination with structural information (multilevel statistical language models and recurrent neural networks, linguistic annotation) from heterogeneous resources (noisy text, dictionaries).

2019

T. Ruzsics,  Lusetti, M., A. Göhring, T. Samardžić  and E. Stark (2019). "Neural text normalization with adapted decoding and PoS features". Natural Language Engineering. 585 - 605. Cambridge University Press. Pre-print

2018

Lusetti, M., T. Ruzsics,  A. Göhring, T. Samardžić  and E. Stark (2018). "Encoder-Decoder Methods for Text Normalization". In Proceedings of the Workshop Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (COLING 2018). Santa Fe, New Mexico, USA, 18- 28. Association for Computational Linguistics.

2017

Ruzsics, T. and T. Samardžić (2017). "Neural Sequence-to-sequence Learning of Internal Word Structure". In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017). Vancouver, Canada, 184-194. Association for Computational Linguistics.

Makarov P., T. Ruzsics, and S. Clematide (2017). "Align and copy: UZH at SIGMORPHON 2017 shared task for morphological reinflection". In Proceedings of the CoNLL- SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, Vancouver, Canada, 49–57. Association for Computational Linguistics. Overall winner of task 1.

2016

Bentz, C., T. Ruzsics,  A. Koplenig, and T. Samardžić (2016). "A comparison between morphological complexity measures: Typological data vs. language corpora". In Proceedings of the Workshop Computational Linguistics for Linguistic Complexity (COLING 2016). Osaka, Japan, 142-153. Association for Computational Linguistics.

"Encoder-Decoder Methods for Text Normalization", SwissText 2018, ZHAW,  Winterthur

"Morphological segmentation", March 2017, Institute of Computational Linguistics Colloquium, University of Zurich