Zobrazeno 1 - 10
of 1 895
pro vyhledávání: '"Soulier, P."'
Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders
With the recent addition of Retrieval-Augmented Generation (RAG), the scope and importance of Information Retrieval (IR) has expanded. As a result, the importance of a deeper understanding of IR models also increases. However, interpretability in IR
Externí odkaz:
http://arxiv.org/abs/2406.19309
Co-speech gestures play a crucial role in the interactions between humans and embodied conversational agents (ECA). Recent deep learning methods enable the generation of realistic, natural co-speech gestures synchronized with speech, but such approac
Externí odkaz:
http://arxiv.org/abs/2406.15111
Autor:
Oldani, V., Manzini, F., Ochner, P., Reguitti, A., Bedin, L. R., Kugel, F., Soulier, J. F., Erece, O., Köseoğlug, D. T., Nehir, Ç., Özişikg, T.
Comet 81P (Wild 2) is characterized by the presence of a prominent-fan shaped dust emission originating from an active source at high latitude on the nucleus, whose axis is assumed to coincide with the comet's rotation axis. Therefore, several author
Externí odkaz:
http://arxiv.org/abs/2405.19975
Autor:
Baldassini, Folco Bertini, Shukor, Mustafa, Cord, Matthieu, Soulier, Laure, Piwowarski, Benjamin
Large Language Models have demonstrated remarkable performance across various tasks, exhibiting the capacity to swiftly acquire new skills, such as through In-Context Learning (ICL) with minimal demonstration examples. In this work, we present a comp
Externí odkaz:
http://arxiv.org/abs/2404.15736
Conversational systems have made significant progress in generating natural language responses. However, their potential as conversational search systems is currently limited due to their passive role in the information-seeking process. One major lim
Externí odkaz:
http://arxiv.org/abs/2402.16608
Autor:
Bronnec, Florian Le, Duong, Song, Ravaut, Mathieu, Allauzen, Alexandre, Chen, Nancy F., Guigue, Vincent, Lumbreras, Alberto, Soulier, Laure, Gallinari, Patrick
State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text generation with
Externí odkaz:
http://arxiv.org/abs/2401.17919
Publikováno v:
Advances in Information Retrieval. ECIR 2024. Lecture Notes in Computer Science, vol 14610
In Information Retrieval, and more generally in Natural Language Processing, adapting models to specific domains is conducted through fine-tuning. Despite the successes achieved by this method and its versatility, the need for human-curated and label
Externí odkaz:
http://arxiv.org/abs/2401.11509
While Large Language Models (LLM) are able to accumulate and restore knowledge, they are still prone to hallucination. Especially when faced with factual questions, LLM cannot only rely on knowledge stored in parameters to guarantee truthful and corr
Externí odkaz:
http://arxiv.org/abs/2401.01780
A peculiarity of conversational search systems is that they involve mixed-initiatives such as system-generated query clarifying questions. Evaluating those systems at a large scale on the end task of IR is very challenging, requiring adequate dataset
Externí odkaz:
http://arxiv.org/abs/2311.06119
Autor:
Erbacher, Pierre, Soulier, Laure
Users often have trouble formulating their information needs into words on the first try when searching online. This can lead to frustration, as they may have to reformulate their queries when retrieved information is not relevant. This can be due to
Externí odkaz:
http://arxiv.org/abs/2311.02737