Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Matej Martinc"'
Publikováno v:
Computational Linguistics, Vol 47, Iss 1, Pp 141-179 (2021)
AbstractWe present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised setting, three different neural c
Externí odkaz:
https://doaj.org/article/3908c0c788ef491899d7a59df24ef10f
Publikováno v:
Frontiers in Aging Neuroscience, Vol 13 (2021)
Background: Advances in machine learning (ML) technology have opened new avenues for detection and monitoring of cognitive decline. In this study, a multimodal approach to Alzheimer's dementia detection based on the patient's spontaneous speech is pr
Externí odkaz:
https://doaj.org/article/d79d2e8745584c26957d0f88438cded0
Autor:
Špela Vintar, Matej Martinc
Publikováno v:
Terminology. 28:129-156
We describe the creation of a knowledge base in the field of karstology using the frame-based approach. Apart from providing a new multilingual resource using manually annotated definitions as the source of structured information, the main focus is o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f41d5ccd3cbfa8013a0fb70b86ce1bf6
https://doi.org/10.1075/term.21005.vin
https://doi.org/10.1075/term.21005.vin
Autor:
Syrielle Montariol, Matej Martinc, Andraž Pelicon, Senja Pollak, Boshko Koloski, Igor Lončarski, Aljoša Valentinčič, Katarina Sitar Šuštar, Riste Ichev, Martin Žnidaršič
Publikováno v:
Communications in Computer and Information Science ISBN: 9783031236327
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::efb1b81d20360b48e2bb77791a362e81
https://doi.org/10.1007/978-3-031-23633-4_1
https://doi.org/10.1007/978-3-031-23633-4_1
Publikováno v:
University of Helsinki
We tackle the problem of neural headline generation in a low-resource setting, where only limited amount of data is available to train a model. We compare the ideal high-resource scenario on English with results obtained on a smaller subset of the sa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3c24d962ae27be554c2bf2accd386b6f
http://hdl.handle.net/10138/346642
http://hdl.handle.net/10138/346642
Publikováno v:
Machine Learning
Learning from texts has been widely adopted throughout industry and science. While state-of-the-art neural language models have shown very promising results for text classification, they are expensive to (pre-)train, require large amounts of data and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3417b86a26fef1e19ba73f6fba3fb6e6
https://doi.org/10.1007/s10994-021-05968-x
https://doi.org/10.1007/s10994-021-05968-x
Publikováno v:
New Generation Computing
The field of bisociative literature-based discovery aims at mining scientific literature to reveal yet uncovered connections between different fields of specialization. This paper outlines several outlier-based literature mining approaches to bridgin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::29885d3bd647135e3cccad68d0e31f2c
https://doi.org/10.1007/s00354-020-00108-w
https://doi.org/10.1007/s00354-020-00108-w
Publikováno v:
From Born-Physical to Born-Virtual: Augmenting Intelligence in Digital Libraries ISBN: 9783031217555
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2e790fe39419d62e88f39b5dd228113b
https://doi.org/10.1007/978-3-031-21756-2_7
https://doi.org/10.1007/978-3-031-21756-2_7
Publikováno v:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5be29c4f950537df83fd3087c67b5d03
https://doi.org/10.18653/v1/2022.semeval-1.12
https://doi.org/10.18653/v1/2022.semeval-1.12
Publikováno v:
Discovery Science ISBN: 9783031188398
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9afe3b87687137f3befeee92ba3e1a39
https://doi.org/10.1007/978-3-031-18840-4_26
https://doi.org/10.1007/978-3-031-18840-4_26