Search Results for author: Roland Mathis

Found 6 papers, 1 papers with code

BETOLD: A Task-Oriented Dialog Dataset for Breakdown Detection

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.

Privacy Preserving

Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems

no code implementations20 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.

Data Augmentation Task-Oriented Dialogue Systems +1

In-Context Learning User Simulators for Task-Oriented Dialog Systems

2 code implementations1 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.

Goal-Oriented Dialogue Systems In-Context Learning +3

Network-based Biased Tree Ensembles (NetBiTE) for Drug Sensitivity Prediction and Drug Sensitivity Biomarker Identification in Cancer

no code implementations18 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.

Mixed-Precision In-Memory Computing

no code implementations16 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

Cannot find the paper you are looking for? You can Submit a new open access paper.