Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Meeus, Quentin"'
While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by introducing
Externí odkaz:
http://arxiv.org/abs/2405.11519
Publikováno v:
Appl. Sci. 2023, 13, 11291
Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into discrete
Externí odkaz:
http://arxiv.org/abs/2211.14320
We explore the benefits that multitask learning offer to speech processing as we train models on dual objectives with automatic speech recognition and intent classification or sentiment classification. Our models, although being of modest size, show
Externí odkaz:
http://arxiv.org/abs/2211.13703
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Thornhill C; Department of Computer Science, KU Leuven, Leuven, Belgium., Meeus Q; Department of Computer Science, KU Leuven, Leuven, Belgium., Peperkamp J; Department of Computer Science, KU Leuven, Leuven, Belgium., Berendt B; Department of Computer Science, KU Leuven, Leuven, Belgium.
Publikováno v:
Frontiers in big data [Front Big Data] 2019 Jun 06; Vol. 2, pp. 11. Date of Electronic Publication: 2019 Jun 06 (Print Publication: 2019).
