Zobrazeno 1 - 10
of 218
pro vyhledávání: '"A. Ghannay"'
Self-Supervised Learning is vastly used to efficiently represent speech for Spoken Language Understanding, gradually replacing conventional approaches. Meanwhile, textual SSL models are proposed to encode language-agnostic semantics. SAMU-XLSR framew
Externí odkaz:
http://arxiv.org/abs/2406.12141
Publikováno v:
LREC-COLING 2024, May 2024, TURIN, Italy
This study is part of the debate on the efficiency of large versus small language models for text classification by prompting.We assess the performance of small language models in zero-shot text classification, challenging the prevailing dominance of
Externí odkaz:
http://arxiv.org/abs/2404.11122
Publikováno v:
The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, Torino, Italy
Intent classification and slot-filling are essential tasks of Spoken Language Understanding (SLU). In most SLUsystems, those tasks are realized by independent modules. For about fifteen years, models achieving both of themjointly and exploiting their
Externí odkaz:
http://arxiv.org/abs/2403.19727
Within the current trend of Pretained Language Models (PLM), emerge more and more criticisms about the ethical andecological impact of such models. In this article, considering these critical remarks, we propose to focus on smallermodels, such as com
Externí odkaz:
http://arxiv.org/abs/2403.18338
Publikováno v:
Proc. Interspeech 2023, 705-709
Over the past few years, self-supervised learned speech representations have emerged as fruitful replacements for conventional surface representations when solving Spoken Language Understanding (SLU) tasks. Simultaneously, multilingual models trained
Externí odkaz:
http://arxiv.org/abs/2307.01323
In the last five years, the rise of the self-attentional Transformer-based architectures led to state-of-the-art performances over many natural language tasks. Although these approaches are increasingly popular, they require large amounts of data and
Externí odkaz:
http://arxiv.org/abs/2207.09152
Autor:
Ibrahim A. Alhagri, Raghad Alsowayan, Siwar Ghannay, Sadeq M. Al-Hazmy, Iqrar Ahmad, Harun Patel, Adel Kadri, Kaiss Aouadi
Publikováno v:
Heliyon, Vol 10, Iss 14, Pp e34561- (2024)
ISoXD2 are well explored among versatile and outstanding class of pharmacophores for the preparation and discovery of drugs. Herein, the electronic absorption and emission spectra of ISoXD2 were investigated in three different solvents. The observed
Externí odkaz:
https://doaj.org/article/a36b8883e1054e94abc53d2be7c13ff6
Autor:
AlRashidi, Etab, Ghannay, Siwar, Albadri, Abuzar E.A.E., Abid, Majdi, Kadri, Adel, Aouadi, Kaiss
Publikováno v:
In Heliyon 30 October 2024 10(20)
We propose to address online speaker diarization as a combination of incremental clustering and local diarization applied to a rolling buffer updated every 500ms. Every single step of the proposed pipeline is designed to take full advantage of the st
Externí odkaz:
http://arxiv.org/abs/2109.06483
Autor:
Alhagri, Ibrahim A., Alsowayan, Raghad, Ghannay, Siwar, Al-Hazmy, Sadeq M., Ahmad, Iqrar, Patel, Harun, Kadri, Adel, Aouadi, Kaiss
Publikováno v:
In Heliyon 30 July 2024 10(14)