Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Rottmann, Kay"'
Deep neural networks are becoming increasingly pervasive in academia and industry, matching and surpassing human performance on a wide variety of fields and related tasks. However, just as humans, even the largest artificial neural networks make mist
Externí odkaz:
http://arxiv.org/abs/2310.19704
Publikováno v:
Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22), pages 83 - 87 December 7, 2022, copyright 2022 Association for Computational Linguistics
Despite recent progress in Natural Language Understanding (NLU), the creation of multilingual NLU systems remains a challenge. It is common to have NLU systems limited to a subset of languages due to lack of available data. They also often vary widel
Externí odkaz:
http://arxiv.org/abs/2212.06346
Autor:
FitzGerald, Jack, Hench, Christopher, Peris, Charith, Mackie, Scott, Rottmann, Kay, Sanchez, Ana, Nash, Aaron, Urbach, Liam, Kakarala, Vishesh, Singh, Richa, Ranganath, Swetha, Crist, Laurie, Britan, Misha, Leeuwis, Wouter, Tur, Gokhan, Natarajan, Prem
We present the MASSIVE dataset--Multilingual Amazon Slu resource package (SLURP) for Slot-filling, Intent classification, and Virtual assistant Evaluation. MASSIVE contains 1M realistic, parallel, labeled virtual assistant utterances spanning 51 lang
Externí odkaz:
http://arxiv.org/abs/2204.08582
Autor:
Rottmann, Kay
In this thesis we investigate the automatic improvements of statistical machine translation systems at runtime based on user feedback. We also propose a framework to use the proposed algorithms in large scale translation settings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b52ebea206425f484013d39a6cfe49fc
https://publikationen.bibliothek.kit.edu/1000052162
https://publikationen.bibliothek.kit.edu/1000052162