A Study on the Impacts of Slot Types and Training Data on Joint Natural Language Understanding in a Spanish Medication Management Assistant Scenario

Autor: Surya Roca, Sophie Rosset, José García, Álvaro Alesanco

Publikováno v: Sensors, Vol 22, Iss 6, p 2364 (2022)

This study evaluates the impacts of slot tagging and training data length on joint natural language understanding (NLU) models for medication management scenarios using chatbots in Spanish. In this study, we define the intents (purposes of the senten

Externí odkaz: https://doaj.org/article/bc04af6f8d5a446b82b625dd33a1f056

DiaBLa: a corpus of bilingual spontaneous written dialogues for machine translation

Autor: Eric Bilinski, Sophie Rosset, Thomas Lavergne, Rachel Bawden

Publikováno v: Language Resources and Evaluation
Language Resources and Evaluation, Springer Verlag, 2020, ⟨10.1007/s10579-020-09514-4⟩

We present a new English–French dataset for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue. The test set contains 144 spontaneous dialogues (5700+ sentences) between native English and French speakers, mediated

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e698dd861325bbabcc39049d15abc4f1
https://doi.org/10.1007/s10579-020-09514-4

Évaluer les systèmes de dialogue apprenant sur le terrain et un cas d'étude pour la compréhension du langage naturel

Autor: Mathilde Veron, Sophie Rosset, Olivier Galibert, Guillaume Bernard

Publikováno v: Workshop NeurIPS 2020 Human in the Loop Dialogue Systems
Workshop NeurIPS 2020 Human in the Loop Dialogue Systems, Dec 2020, Virtual only, United States
HAL

On-the-job learning consists in continuously learning while being used in production, in an open environment, meaning that the system has to deal on its own with situations and elements never seen before. The kind of systems that seem to be especiall

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::378db199cbcd4e6045c2f2fe3eaeac63
https://hal.archives-ouvertes.fr/hal-03301611/file/NeurIPS_2020_HLDS_on_the_job_NLU_v4_camera_ready.pdf

Lessons Learned from the Usability Evaluation of a Simulated Patient Dialogue System

Autor: Catherine Thomas, Leonardo Campillos-Llanos, Pierre Zweigenbaum, Sophie Rosset, Antoine Neuraz, Eric Bilinski

Publikováno v: Digital.CSIC. Repositorio Institucional del CSIC
instname
Journal of Medical Systems
Journal of Medical Systems, Springer Verlag (Germany), 2021, 45 (7), ⟨10.1007/s10916-021-01737-4⟩
Journal of Medical Systems, 2021, 45 (7), pp.69. ⟨10.1007/s10916-021-01737-4⟩
Journal of Medical Systems, 2021, 45 (7), ⟨10.1007/s10916-021-01737-4⟩
Digital.CSIC: Repositorio Institucional del CSIC
Consejo Superior de Investigaciones Científicas (CSIC)

International audience; Simulated consultations through virtual patients allow medical students to practice history-taking skills. Ideally, applications should provide interactions in natural language and be multi-case, multi-specialty. Nevertheless,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e5d81d3b7aa89a64dc6519b05e21fb9c
http://hdl.handle.net/10261/243697

De l'utilisabilité des modèles Transformers appliqués à une tâche de réponse aux questions en français

Autor: Christophe Servan, Oralie Cattan, Sophie Rosset

Publikováno v: RANLP
Recent Advances in Natural Language Processing (RANLP)
Recent Advances in Natural Language Processing (RANLP), Sep 2021, Varna, Bulgaria
HAL

For many tasks, state-of-the-art results have been achieved with Transformer-based architectures, resulting in a paradigmatic shift in practices from the use of task-specific architectures to the fine-tuning of pre-trained language models. The ongoin

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06b964f0abf533ec96624a046c2fb5ac
https://doi.org/10.26615/978-954-452-072-4_029