Zobrazeno 1 - 10
of 1 535
pro vyhledávání: '"Couceiro P"'
Autor:
Elizabeth, Michelle, Veyret, Morgan, Couceiro, Miguel, Dusek, Ondrej, Rojas-Barahona, Lina M.
Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations. However, they underperform compared to previous approaches in task-oriented dialogue (TOD), wherein reasoning and accessing ext
Externí odkaz:
http://arxiv.org/abs/2412.01262
Autor:
Monnin, Pierre, Nousradine, Cherif-Hassan, Jarnac, Lucas, Zuckerman, Laurel, Couceiro, Miguel
Knowledge graphs (KGs) have become ubiquitous publicly available knowledge sources, and are nowadays covering an ever increasing array of domains. However, not all knowledge represented is useful or pertaining when considering a new application or sp
Externí odkaz:
http://arxiv.org/abs/2408.14658
Autor:
Qureshi, Rameez, Es-Sebbani, Naïm, Galárraga, Luis, Graham, Yvette, Couceiro, Miguel, Bouraoui, Zied
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes, as well as
Externí odkaz:
http://arxiv.org/abs/2408.09489
Autor:
Lepage, Yves, Couceiro, Miguel
This work presents a formalization of analogy on numbers that relies on generalized means. It is motivated by recent advances in artificial intelligence and applications of machine learning, where the notion of analogy is used to infer results, creat
Externí odkaz:
http://arxiv.org/abs/2407.18770
The calibration of predictive distributions has been widely studied in deep learning, but the same cannot be said about the more specific epistemic uncertainty as produced by Deep Ensembles, Bayesian Deep Networks, or Evidential Deep Networks. Althou
Externí odkaz:
http://arxiv.org/abs/2407.12211
Knowledge Graphs (KGs) are a major asset for companies thanks to their great flexibility in data representation and their numerous applications, e.g., vocabulary sharing, Q/A or recommendation systems. To build a KG it is a common practice to rely on
Externí odkaz:
http://arxiv.org/abs/2405.16929
Autor:
Riz, Luigi, Povoli, Sergio, Caraffa, Andrea, Boscaini, Davide, Mekhalfi, Mohamed Lamine, Chippendale, Paul, Turtiainen, Marjut, Partanen, Birgitta, Ballester, Laura Smith, Noguera, Francisco Blanes, Franchi, Alessio, Castelli, Elisa, Piccinini, Giacomo, Marchesotti, Luca, Couceiro, Micael Santos, Poiesi, Fabio
Berry picking has long-standing traditions in Finland, yet it is challenging and can potentially be dangerous. The integration of drones equipped with advanced imaging techniques represents a transformative leap forward, optimising harvests and promi
Externí odkaz:
http://arxiv.org/abs/2405.07550
In this paper we are interested in the fine-grained complexity of deciding whether there is a homomorphism from an input graph $G$ to a fixed graph $H$ (the $H$-Coloring problem). The starting point is that these problems can be viewed as constraint
Externí odkaz:
http://arxiv.org/abs/2404.09798
In the field of spoken language understanding, systems like Whisper and Multilingual Massive Speech (MMS) have shown state-of-the-art performances. This study is dedicated to a comprehensive exploration of the Whisper and MMS systems, with a focus on
Externí odkaz:
http://arxiv.org/abs/2402.07513
Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages. Some of these models employ language adapters in their formulation, which helps to improve monol
Externí odkaz:
http://arxiv.org/abs/2310.07423