Abstract Submissions to the Open Session
The MT Marathon will again host an open session with poster presentations related to MT/NLP research and open-source tools. We invite students, developers and researchers to submit short abstracts (1 page) featuring previously published results, open-source tool demos, and work in progress. Abstracts are lightly reviewed for topical scope, and all relevant submissions will be accepted for presentation.
To make a submission, please send an e-mail to mtm24-submissions@ufal.mff.cuni.cz, with the following information:
- Names of all authors and their affiliation
- A single PDF (or plain-text) file containing the abstract
Accepted abstracts:
- Dominik Macháček, Ondřej Bojar, Raj Dabre (Charles University, NICT), Whisper-Streaming demo
- Tomasz Limisiewicz, David Mareček (Charles University), Multilingual DAMA for Debiasing Translation
- Gianluca Vico, Jindřich Libovický (Charles University), Alignable Tokenization for Machine Translation.
- Tsegay Kiros, Statistical Machine Translator for English to Tigrigna Translation
- Ondřej Plátek, Zdeněk Kasner, Ondřej Dušek (Charles University), factgenie: A Framework for Span-based Evaluation of Generated Texts; How can we help evaluate machine translation?
- Wojciech Chojnowski, Artur Kot, Mikołaj Koszowski, Mieszko Rutkowski, Artur Nowakowski, Kamil Guttmann, Mikołaj Pokrywka (Allegro, Laniqo), MultiSlav: Multilingual Slavic Neural Machine Translation Models for effective zero-shot Cross-Linguality
- Mikołaj Pokrywka, Wojciech Kusa, Mikołaj Koszowski, Mieszko Rutkowski (Allegro), MT Beyond Text Horizons: Multimodal and Contextualised MT in the E-commerce Domain
- Seth Aycock (University of Amsterdam), Can Large Language Models Really Learn to Translate an Under-Resourced Language from One Grammar Book?
- Wiktor Kamzela (Poznań University of Technology), Vocabulary-constrained multilingual story generation for language learning
- Jędrzej Warczyński (Poznań University of Technology), Interpretable Rule-Based Data-to-Text Generation Using Large Language Models
- Maria Zafar, Rejwanul Haque, Andy Way (South East Technological University, Carlow, Ireland), A Framework for Distillation and Strategic Teacher Selection
- Miroslav Hrabal, Ondřej Bojar (Charles University), A web-based toolkit for MT evaluation
- Andrei Manea, Jindřich Libovický (Charles University), Cross-lingual Transfer for Language-Vision Models with just a handful of Parallel data
- Eduardo Sánchez, Pierre Andrews, Pontus Stenetorp, Mikel Artetxe, Marta R. Costa-jussà (University College London, Meta, University of the Basque Country), Gender-specific Machine Translation with Large Language Models
- Tom Kocmi, Vilém Zouhar, Christian Federmann, and Matt Post (Microsoft, ETH Zürich), Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies