Zobrazeno 1 - 10
of 15 355
pro vyhledávání: '"Doh, A."'
Text-to-Music Retrieval, finding music based on a given natural language query, plays a pivotal role in content discovery within extensive music databases. To address this challenge, prior research has predominantly focused on a joint embedding of mu
Externí odkaz:
http://arxiv.org/abs/2410.03264
Recent psycholinguistic research has compared human reading times to surprisal estimates from language models to study the factors shaping human sentence processing difficulty. Previous studies have shown a strong fit between surprisal values from Tr
Externí odkaz:
http://arxiv.org/abs/2409.11250
We tackle the challenges of decentralized multi-robot navigation in environments with nonconvex obstacles, where complete environmental knowledge is unavailable. While reactive methods like Artificial Potential Field (APF) offer simplicity and effici
Externí odkaz:
http://arxiv.org/abs/2409.10332
Autor:
Albert, Julien, Balfroid, Martin, Doh, Miriam, Bogaert, Jeremie, La Fisca, Luca, De Vos, Liesbet, Renard, Bryan, Stragier, Vincent, Jean, Emmanuel
Recommender systems have become integral to our digital experiences, from online shopping to streaming platforms. Still, the rationale behind their suggestions often remains opaque to users. While some systems employ a graph-based approach, offering
Externí odkaz:
http://arxiv.org/abs/2409.06297
For large language models (LLMs) like NLLB and GPT, translating idioms remains a challenge. Our goal is to enhance translation fidelity by improving LLM processing of idiomatic language while preserving the original linguistic style. This has a signi
Externí odkaz:
http://arxiv.org/abs/2407.03518
Autor:
Doh, Miriam, Karagianni, and Anastasia
This study delves into gender classification systems, shedding light on the interaction between social stereotypes and algorithmic determinations. Drawing on the "averageness theory," which suggests a relationship between a face's attractiveness and
Externí odkaz:
http://arxiv.org/abs/2407.17474
Autor:
Oh, Byung-Doh, Schuler, William
Predictions of word-by-word conditional probabilities from Transformer-based language models are often evaluated to model the incremental processing difficulty of human readers. In this paper, we argue that there is a confound posed by the most commo
Externí odkaz:
http://arxiv.org/abs/2406.10851
Word embedding has become an essential means for text-based information retrieval. Typically, word embeddings are learned from large quantities of general and unstructured text data. However, in the domain of music, the word embedding may have diffic
Externí odkaz:
http://arxiv.org/abs/2404.13569
Recent studies have shown that as Transformer-based language models become larger and are trained on very large amounts of data, the fit of their surprisal estimates to naturalistic human reading times degrades. The current work presents a series of
Externí odkaz:
http://arxiv.org/abs/2402.02255
Autor:
Doh, Miriam, Rodrigues, Caroline Mazini, Boutry, Nicolas, Najman, Laurent, Mancas, Matei, Bersini, Hugues
With Artificial Intelligence (AI) influencing the decision-making process of sensitive applications such as Face Verification, it is fundamental to ensure the transparency, fairness, and accountability of decisions. Although Explainable Artificial In
Externí odkaz:
http://arxiv.org/abs/2403.08789