- home
- Advanced Search
Advanced search in Research outcomes
Filters
Clear AllFilters
Clear AllLoading
- publication . Preprint . 2020Open Access EnglishAuthors:Limisiewicz, Tomasz; Mareček, David;
With the recent success of pre-trained models in NLP, a significant focus was put on interpreting their representations. One of the most prominent approaches is structural probing (Hewitt and Manning, 2019), where a linear projection of language vector space is performe...
- publication . Article . 2020Open Access ItalianAuthors:Monachini, Monica; Frontini, Francesca;Publisher: Accademia University Press
National audience; Il 1° ottobre 2015 il MIUR firma l'adesione dell'Italia a CLARIN-ERIC, l'infrastruttura di ricerca che offre risorse e tecnologie linguistiche dedicate al settore delle scienze del linguaggio e delle scienze umane e sociali. Questo articolo intende fo...
- publication . Other literature type . 2020Open Access EnglishAuthors:Koolen, Marijn; Kumpulainen, Sanna; Melgar-Estrada, Liliana;Project: NWO | CLARIAH Common Lab Resear... (2300184354)
The concept of “scholarly primitive” has been widely welcomed both by humanists and system designers in the humanities, due to the fact that it made it possible to have a solid conceptual basis for the operationalization of the essential functionalities required for adv...
- publication . Preprint . 2020Open Access EnglishAuthors:Kvapilíková, Ivana; Kocmi, Tom; Bojar, Ondřej;
This paper presents a description of CUNI systems submitted to the WMT20 task on unsupervised and very low-resource supervised machine translation between German and Upper Sorbian. We experimented with training on synthetic data and pre-training on a related language pa...
- publication . Preprint . 2020Open Access EnglishAuthors:Kocmi, Tom; Limisiewicz, Tomasz; Stanovsky, Gabriel;Project: EC | Bergamot (825303)
Gender bias in machine translation can manifest when choosing gender inflections based on spurious gender correlations. For example, always translating doctors as men and nurses as women. This can be particularly harmful as models become more popular and deployed within...
- publication . Preprint . Conference object . 2020Open Access EnglishAuthors:Martin Vastl; Daniel Zeman; Rudolf Rosa;
We present our submission to the SIGTYP 2020 Shared Task on the prediction of typological features. We submit a constrained system, predicting typological features only based on the WALS database. We investigate two approaches. The simpler of the two is a system based o...
- publication . Preprint . 2020Open Access EnglishAuthors:Limisiewicz, Tomasz; Mareček, David;
Neural networks trained on natural language processing tasks capture syntax even though it is not provided as a supervision signal. This indicates that syntactic analysis is essential to the understating of language in artificial intelligence systems. This overview pape...
- publication . Part of book or chapter of book . Preprint . 2020Open AccessAuthors:Tomáš Musil; David Mareček; Rudolf Rosa;Publisher: Springer International Publishing
Multiple studies have probed representations emerging in neural networks trained for end-to-end NLP tasks and examined what word-level linguistic information may be encoded in the representations. In classical probing, a classifier is trained on the representations to e...
- publication . Preprint . 2020Open Access EnglishAuthors:Hajič, Jan; Bejček, Eduard; Hlaváčová, Jaroslava; Mikulová, Marie; Straka, Milan; Štěpánek, Jan; Štěpánková, Barbora;
We present a richly annotated and genre-diversified language resource, the Prague Dependency Treebank-Consolidated 1.0 (PDT-C 1.0), the purpose of which is - as it always been the case for the family of the Prague Dependency Treebanks - to serve both as a training data ...
- publication . Preprint . 2020Open Access EnglishAuthors:Straka, Milan; Straková, Jana;
We present our contribution to the EvaLatin shared task, which is the first evaluation campaign devoted to the evaluation of NLP tools for Latin. We submitted a system based on UDPipe 2.0, one of the winners of the CoNLL 2018 Shared Task, The 2018 Shared Task on Extrins...