Search Results for author: Lina M. Rojas-Barahona

Found 22 papers, 1 papers with code

WEBDial, a Multi-domain, Multitask Statistical Dialogue Framework with RDF

no code implementations8 Jan 2024 Morgan Veyret, Jean-Baptiste Duchene, Kekeli Afonouvi, Quentin Brabant, Gwenole Lecorve, Lina M. Rojas-Barahona

Typically available dialogue frameworks have adopted a semantic representation based on dialogue-acts and slot-value pairs.

Unsupervised Auditory and Semantic Entrainment Models with Deep Neural Networks

no code implementations22 Dec 2023 Jay Kejriwal, Stefan Benus, Lina M. Rojas-Barahona

Speakers tend to engage in adaptive behavior, known as entrainment, when they become similar to their interlocutor in various aspects of speaking.


KGConv, a Conversational Corpus grounded in Wikidata

no code implementations29 Aug 2023 Quentin Brabant, Gwenole Lecorve, Lina M. Rojas-Barahona, Claire Gardent

We present KGConv, a large, conversational corpus of 71k conversations where each question-answer pair is grounded in a Wikidata fact.

Knowledge Graphs Question Answering +3

Interpreting Vision and Language Generative Models with Semantic Visual Priors

no code implementations28 Apr 2023 Michele Cafagna, Lina M. Rojas-Barahona, Kees Van Deemter, Albert Gatt

When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence.

Few-Shot Structured Policy Learning for Multi-Domain and Multi-Task Dialogues

no code implementations22 Feb 2023 Thibault Cordier, Tanguy Urvoy, Fabrice Lefevre, Lina M. Rojas-Barahona

Reinforcement learning has been widely adopted to model dialogue managers in task-oriented dialogues.

"Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking

no code implementations29 Jul 2022 Léo Jacqmin, Lina M. Rojas-Barahona, Benoit Favre

DST has received a lot of interest in recent years with the text-to-text paradigm emerging as the favored approach.

Dialogue State Tracking

CoQAR: Question Rewriting on CoQA

no code implementations LREC 2022 Quentin Brabant, Gwenole Lecorve, Lina M. Rojas-Barahona

CoQAR can be used in the supervised learning of three tasks: question paraphrasing, question rewriting and conversational question answering.

Question Rewriting

Is the User Enjoying the Conversation? A Case Study on the Impact on the Reward Function

no code implementations13 Jan 2021 Lina M. Rojas-Barahona

The impact of user satisfaction in policy learning task-oriented dialogue systems has long been a subject of research interest.

Representation Learning Task-Oriented Dialogue Systems

Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation

no code implementations25 Nov 2020 Thibault Cordier, Tanguy Urvoy, Lina M. Rojas-Barahona, Fabrice Lefèvre

We notably propose a randomised exploration policy which allows for a seamless hybridisation of the learned policy and the expert.

Imitation Learning Q-Learning +1

Multi-domain Neural Network Language Generation for Spoken Dialogue Systems

no code implementations NAACL 2016 Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, David Vandyke, Steve Young

Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of domains.

Domain Adaptation Spoken Dialogue Systems +1

Building and Exploiting a Corpus of Dialog Interactions between French Speaking Virtual and Human Agents

no code implementations LREC 2012 Lina M. Rojas-Barahona, Alej Lorenzo, ra, Claire Gardent

We describe the acquisition of a dialog corpus for French based on multi-task human-machine interactions in a serious game setting.

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