no code implementations • CAI (COLING) 2022 • Silvia Terragni, Bruna Guedes, Andre Manso, Modestas Filipavicius, Nghia Khau, Roland Mathis
Ideally TOD systems should be able to detect dialog breakdowns to prevent users from quitting a conversation and to encourage them to interact with the system again.
no code implementations • 20 Feb 2024 • Ivan Sekulić, Silvia Terragni, Victor Guimarães, Nghia Khau, Bruna Guedes, Modestas Filipavicius, André Ferreira Manso, Roland Mathis
Notably, we have observed that fine-tuning enhances the simulator's coherence with user goals, effectively mitigating hallucinations -- a major source of inconsistencies in simulator responses.
2 code implementations • 1 Jun 2023 • Silvia Terragni, Modestas Filipavicius, Nghia Khau, Bruna Guedes, André Manso, Roland Mathis
This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach.
no code implementations • 18 Aug 2018 • Ali Oskooei, Matteo Manica, Roland Mathis, Maria Rodriguez Martinez
We present the Network-based Biased Tree Ensembles (NetBiTE) method for drug sensitivity prediction and drug sensitivity biomarker identification in cancer using a combination of prior knowledge and gene expression data.
no code implementations • 29 Mar 2018 • Matteo Manica, Joris Cadow, Roland Mathis, María Rodríguez Martínez
Reliable identification of molecular biomarkers is essential for accurate patient stratification.
no code implementations • 16 Jan 2017 • Manuel Le Gallo, Abu Sebastian, Roland Mathis, Matteo Manica, Heiner Giefers, Tomas Tuma, Costas Bekas, Alessandro Curioni, Evangelos Eleftheriou
As CMOS scaling reaches its technological limits, a radical departure from traditional von Neumann systems, which involve separate processing and memory units, is needed in order to significantly extend the performance of today's computers.
Emerging Technologies