Search

Showing total 5 results
Start Over Topic [info.info-cl]computer science [cs]/computation and language [cs.cl]
5 results

1. Privacy-preserving mimic models for clinical named entity recognition in French

Author

Nesrine Bannour, Perceval Wajsbürt, Bastien Rance, Xavier Tannier, Aurélie Névéol, Information, Langue Ecrite et Signée (ILES), Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Sciences et Technologies des Langues (STL), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé (LIMICS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Sorbonne Paris Nord, Centre de Recherche des Cordeliers (CRC (UMR_S_1138 / U1138)), École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité), Health data- and model- driven Knowledge Acquisition (HeKA), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche des Cordeliers (CRC (UMR_S_1138 / U1138)), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité)-École Pratique des Hautes Études (EPHE), This work was supported by ITMO Cancer Aviesan. The funding organization had no role in the conceptualization, design, data collection and analysis, preparation of the paper, or the decision to publish it., Tannier, Xavier, École pratique des hautes études (EPHE), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité)-École pratique des hautes études (EPHE)

Subjects
Computer, Narration, Mimic learning, Privacy, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Natural language processing, Confidentiality Datasets as topic, Humans, Electronic health records, Health Informatics, Neural networks, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Computer Science Applications
Abstract

International audience; A vast amount of crucial information about patients resides solely in unstructured clinical narrative notes. There has been a growing interest in clinical Named Entity Recognition (NER) task using deep learning models. Such approaches require sufficient annotated data. However, there is little publicly available annotated corpora in the medical field due to the sensitive nature of the clinical text. In this paper, we tackle this problem by building privacy-preserving shareable models for French clinical Named Entity Recognition using the mimic learning approach to enable the knowledge transfer through a teacher model trained on a private corpus to a student model. This student model could be publicly shared without any access to the original sensitive data. We evaluated three privacy-preserving models using three medical corpora and compared the performance of our models to those of baseline models such as dictionary-based models. An overall macro F-measure of 70.6% could be achieved by a student model trained using silver annotations produced by the teacher model, compared to 85.7% for the original private teacher model. Our results revealed that these privacy-preserving mimic learning models offer a good compromise between performance and data privacy preservation.

Published
2022

2. Combining Uncore Frequency and Dynamic Power Capping to Improve Power Savings

Author

Guermouche, Amina, STatic Optimizations, Runtime Methods (STORM), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université de Bordeaux (UB), Institut Polytechnique de Bordeaux (Bordeaux INP), and This work was supported by the European High-Performance Computing Joint Undertaking EuroHPC under grant agreement No 955495 (MICROCARD) co-funded by the Horizon 2020 program of the European Union (EU), the French National Research Agency ANR, the German Federal Ministry of Education and Research, the Italian ministry of economic development, the Swiss State Secretariat for Education, Research and Innovation, the Austrian Research Promotion Agency FFG, and the Research Council of Norway. Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr).

Subjects
Energy consumption, Uncore frequency, Power consumption, Power capping, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
Abstract

International audience; The US Department of Energy sets a limit of 20 to 30 MW for future exascale machines. In order to control their power consumption, modern processors provide many features. Power capping and uncore frequency scaling are examples of such features which allow to limit the power consumed by a processor. In this paper, we propose to combine dynamic power capping to uncore frequency scaling. We propose DUFP, an extension of DUF, an existing tool which dynamically adapts uncore frequency. DUFP dynamically adapts the processor power cap to the application needs. Finally, just like DUF, DUFP can tolerate performance loss up to a user-defined limit. With a controlled impact on performance, DUFP is able to provide power savings with no energy loss. The evaluation of DUFP shows that it manages to stay within the user-defined slowdown limits for most of the studied applications. Moreover, combining uncore frequency scaling to power capping: (i) improves power consumption by up to 13.98 % with additional energy savings for applications where uncore frequency scaling has a limited impact, (ii) improves power consumption by up to 7.90 % compared to using uncore frequency scaling by itself and (iii) leads to more than 5 % power savings at 5 % tolerated slowdown with no energy loss for most applications.

Published
2022

3. MORDigital: the advent of a new lexicographical Portuguese project

Author

Costa, R., Salgado, A., Khan, A., Carvalho, S., Romary, L., Almeida, B., Ramos, M., Khemakhem, M., Silva, R., Tasovac, T., Centro de Linguística da Universidade Nova de Lisboa (CLUNL), Faculty of Social and Human Sciences (NOVAFCSH), Universidade Nova de Lisboa = NOVA University Lisbon (NOVA)-Universidade Nova de Lisboa = NOVA University Lisbon (NOVA), Academia das Ciências de Lisboa, Istituto di Linguistica Computazionale 'Antonio Zampolli' (CNR-ILC), Consiglio Nazionale delle Ricerche [Roma] (CNR), Centro de Línguas, Literaturas e Culturas (CLLC), Universidade de Aveiro, Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ROSSIO – Ciências Sociais, Artes e Humanidades (ROSSIO), ArcaScience, Belgrade Center for Digital Humanities (BCDH), This paper is supported by (1) the MORDigital –Digitalização do Diccionario da Lingua Portugueza de António de Morais Silva [PTDC/LLT-LIN/6841/2020] project financed by the Portuguese National Funding through the FCT –Fundação para a Ciência e Tecnologia (2) Portuguese National Funding through the FCT –Fundação para a Ciência e Tecnologia as part of the project Centro de Linguística da Universidade NOVA de Lisboa –UID/LIN/03213/2020 and (3) the European Union’s Horizon 2020 research and innovation programme under grant agreement No 731015 (ELEXIS) (European Lexicographic Infrastructure)., National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR), and Romary, Laurent

Subjects
Standards, Lexicography, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], GROBID-Dictionaries, Ontologies, [INFO.INFO-DL]Computer Science [cs]/Digital Libraries [cs.DL], [INFO.INFO-DL] Computer Science [cs]/Digital Libraries [cs.DL], Legacy dictionary, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Digital humanities
Abstract

International audience; MORDigital is a newly funded Portuguese lexicographical project that aims to produce highquality and searchable digital versions of the first three editions (1789; 1813; 1823) of the Diccionario da Lingua Portugueza by António de Morais Silva, preserving and making accessible this important work of European heritage. This paper will describe the current state of the art, the project, its objectives and the methodology proposed, the latter of which is based on a rigorous linguistic analysis and will also include steps necessary for the ontologisation of knowledge contained in and relating to the text. A section will be dedicated to the various investigation domains of the project description. The output of the project will be made available via a dedicated platform.

Published
2021
Full Text
View/download PDF

4. MOR Digital: The Advent of a New Lexicographical Portuguese Project

Author

Costa, Rute, Salgado, Ana, Khan, Anas, Carvalho, Sara, Romary, Laurent, Almeida, Bruno, Ramos, Margarida, Khemakhem, Mohamed, Silva, Raquel, Tasovac, Toma, Centro de Linguística da Universidade Nova de Lisboa (CLUNL), Faculty of Social and Human Sciences (NOVAFCSH), Universidade Nova de Lisboa = NOVA University of Lisboa (NOVA)-Universidade Nova de Lisboa = NOVA University of Lisboa (NOVA), Academia das Ciências de Lisboa, Istituto di Linguistica Computazionale 'Antonio Zampolli' (CNR-ILC), Consiglio Nazionale delle Ricerche [Roma] (CNR), Centro de Línguas, Literaturas e Culturas (CLLC), Universidade de Aveiro, Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ROSSIO – Ciências Sociais, Artes e Humanidades (ROSSIO), ArcaScience, Belgrade Center for Digital Humanities (BCDH), and This paper is supported by (1) the MORDigital –Digitalização do Diccionario da Lingua Portugueza de António de Morais Silva [PTDC/LLT-LIN/6841/2020] project financed by the Portuguese National Funding through the FCT –Fundação para a Ciência e Tecnologia (2) Portuguese National Funding through the FCT –Fundação para a Ciência e Tecnologia as part of the project Centro de Linguística da Universidade NOVA de Lisboa –UID/LIN/03213/2020 and (3) the European Union’s Horizon 2020 research and innovation programme under grant agreement No 731015 (ELEXIS) (European Lexicographic Infrastructure).

Subjects
Standards, Lexicography, GROBID-Dictionaries, Ontologies, [INFO.INFO-DL]Computer Science [cs]/Digital Libraries [cs.DL], Legacy dictionary, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Digital humanities
Abstract

International audience; MORDigital is a newly funded Portuguese lexicographical project that aims to produce highquality and searchable digital versions of the first three editions (1789; 1813; 1823) of the Diccionario da Lingua Portugueza by António de Morais Silva, preserving and making accessible this important work of European heritage. This paper will describe the current state of the art, the project, its objectives and the methodology proposed, the latter of which is based on a rigorous linguistic analysis and will also include steps necessary for the ontologisation of knowledge contained in and relating to the text. A section will be dedicated to the various investigation domains of the project description. The output of the project will be made available via a dedicated platform.

Published
2021

5. Deep Variational Metric Learning for Transfer of Expressivity in Multispeaker Text to Speech

Author

Vincent Colotte, Ajinkya Kulkarni, Denis Jouvet, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Experiments presented in this paper were carried out using the Grid5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations. (see https://www.grid5000.fr), and Grid'5000

Subjects
Computer science, Speech recognition, deep metric learning, Contrast (statistics), 020206 networking & telecommunications, Speech synthesis, 02 engineering and technology, expressivity, computer.software_genre, Speaker recognition, Autoencoder, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Identity (music), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Metric (mathematics), 0202 electrical engineering, electronic engineering, information engineering, variational autoencoder, 020201 artificial intelligence & image processing, Expressivity (genetics), text-to-speech, Representation (mathematics), computer
Abstract

In this paper, we propose an approach relying on multiclass N-pair loss based deep metric learning in recurrent conditional variational autoencoder (RCVAE). We used RCVAE for implementation of multispeaker expressive text-to-speech (TTS) system. The proposed approach condition text-to-speech system on speaker embeddings, and leads to clustering the latent space representation with respect to emotion. The deep metric learning helps to reduce the intra-class variance and increase the inter-class variance in latent space. Thus, we present multiclass N-pair loss to enhance the meaningful representation of the latent space. For representing the speaker, we extracted speaker embed-dings from the x-vector based speaker recognition model trained on speech data from many speakers. To predict the vocoder features, we used RCVAE for the acoustic modeling, in which the model is conditioned on the textual features as well as on the speaker embedding. We transferred the expressivity by using the mean of the latent variables for each emotion to generate expressive speech in different speaker's voices for which no expressive speech data is available. We compared the results with those of the RCVAE model without multiclass N-pair loss as baseline model. The performance measured by mean opinion score (MOS), speaker MOS, and expressive MOS shows that N-pair loss based deep metric learning significantly improves the transfer of expressivity in the target speaker's voice in synthesized speech.

Published
2020