Conférences - Traitement automatique des langues, Linguistique informatique

Machine Learning Prague s.r.o

Central Europe's largest practical conference in Machine Learning, AI and Deep Learning applications. Join over 1000 participants from over 35 countries to participate in 10 workshops and 23 talks.

Email.: gonzalo@mlprague.com

IEEE Signal Processing Society

Reconnaissance de formes et traitement d'image, vision par ordinateur,    Acoustique et vibrations

Huazhong University of Science and Technology(HUST) in Wuhan

Spoken language is the favored media of communication between human beings whether face-to-face or through various communication tools such as the phone, voice chat applications or even the general media like the radio or TV. Hence, adding conversational interfaces to various types of computer software and hardware devices will make them more natural. To achieve this goal, there are still multiple challenges at all the levels from speech recognition and synthesis, spoken language understanding and generation as well as dialog management. To meet these challenges, interdisciplinary work at the cross roads between linguistics, AI, Data Science, and Cognitive Science is carried by researchers around the world.

The goal of this track is to be a forum for scholars and scientists to present their empirical research, and well-grounded theory related to Spoken Language Processing as well as to Dialog and Conversational Systems.

Email.: mzkurdi@gmail.com

Spoken Language Processing, Speech Recognition and Synthesis, Dialog and Conversational Systems, speaker recognition, Spoken Language interfaces, emotion in speech

IMT Atlantique & CNRS UMR 6285 Lab-STICC

G21C (Grapholinguistics in the 21st Century) is a biennial conference bringing together disciplines concerned with grapholinguistics and more generally the study writing systems and their representation in written communication. The conference aims to reflect on the current state of research in the area, and on the role that writing and writing systems play in neighboring disciplines like computer science and information technology, communication, typography, psychology, and pedagogy. In particular it aims to study the effect of the growing importance of Unicode with regard to the future of reading and writing in human societies. Reflecting the richness of perspectives on writing systems, G21C is actively interdisciplinary, and welcomes proposals from researchers from the fields of computer science and information technology, linguistics, communication, pedagogy, psychology, history, and the social sciences.

Organizer;     Email.: grafematik2020@sciencesconf.org

Grapholinguistics, writing systems, natural language processing, cognitive sciences, history of writing, education

Association for Computational Linguistics (ACL)

Under the auspices of FoLLI the European Summer School in Logic, Language, and Information (ESSLLI) is organized every year in a different European country. It takes place over two weeks in the European Summer, hosts approximately 50 different courses at both the introductory and advanced levels, attracting around 400 participants each year from all the world. The main focus of the program of the summer schools is the interface between linguistics, logic and computation, with special emphasis in human linguistic and cognitive ability.

Théorie de l'information, fondations de l'informatique,    Formation en informatique

Funded by the European Research Council

The field of natural language semantics has undergone what some refer to as an ‘experimental turn’ and is arguably currently undergoing a ‘computational turn’. By expanding the toolbox available to the semanticist, these two turns have the effect of expanding the phenomena that can be explained and the varieties of semantic explanation that can be offered. For example, experimental methods can help distinguish between alternative explanations of semantic effects, e.g. whether to classify controversial phenomena as implicatures or presuppositions. Similarly, computational models of semantics can generate fine-grained and non-categorical predictions that can fruitfully be tested experimentally. And both kinds of methods can be used to ask questions about the emergence of semantic structures in language, including which factors influence their distribution and typology. Given this wider toolbox and purview, we aim to gather a workshop to showcase exciting new work that develops new semantic explanations using experimental and computational methods, as well as to invite broader reflection on the methodology of semantics now and in its future. Topics of potential interest include but are not limited to: * Experimental semantics and pragmatics * Graded/non-categorical semantic theories and explanations * Information-theoretic measures and explanations in semantics and pragmatics * Semantic universals * Learnability and evolution of semantics and pragmatics * Bayesian approaches to semantics and pragmatics * Probing neural models for learned semantic representations * Semantics in emergent communication protocols * The methodology of semantics We invite anonymized submission of abstracts of 2 pages (12 pt font; 1in or 2.5cm margins) — with an extra page for references of figures — on new research on topics related to those listed above by February 15.

Réseaux de neurones et intelligence artificielle, apprentissage automatique,    Cours et évènements pour étudiants en mathématiques

Funded by the European Research Council

The field of natural language semantics has undergone what some refer to as an ‘experimental turn’ and is arguably currently undergoing a ‘computational turn’. By expanding the toolbox available to the semanticist, these two turns have the effect of expanding the phenomena that can be explained and the varieties of semantic explanation that can be offered. For example, experimental methods can help distinguish between alternative explanations of semantic effects, e.g. whether to classify controversial phenomena as implicatures or presuppositions. Similarly, computational models of semantics can generate fine-grained and non-categorical predictions that can fruitfully be tested experimentally. And both kinds of methods can be used to ask questions about the emergence of semantic structures in language, including which factors influence their distribution and typology. Given this wider toolbox and purview, we aim to gather a workshop to showcase exciting new work that develops new semantic explanations using experimental and computational methods, as well as to invite broader reflection on the methodology of semantics now and in its future.

Experimental semantics and pragmatics * Graded/non-categorical semantic theories and explanations * Information-theoretic measures and explanations in semantics and pragmatics * Semantic universals * Learnability and evolution of semantics and pragmatics * Bayesian approaches to semantics and pragmatics * Probing neural models for learned semantic representations * Semantics in emergent communication protocols * The methodology of semantics

Réseaux de neurones et intelligence artificielle, apprentissage automatique,    Cours et évènements pour étudiants en mathématiques

CIRM – Centre International de Rencontres Mathématiques

Cours et évènements pour étudiants en mathématiques,    Mathématiques appliquées (en général)

SemEval has evolved from the SensEval word sense disambiguation evaluation series. The SemEval wikipedia entry and the ACL SemEval Wiki provide a more detailed historical overview. SemEval-2020 will be the 14th workshop on semantic evaluation.

Reconnaissance de formes et traitement d'image, vision par ordinateur,    Soft computing, algorithmes évolutionnaires, domaine des métaheuristiques, logique floue

INTERSPEECH has grown into the world's largest technical conference focused on speech processing and application with over 1000 attendees and over 600 papers. The conferences emphasize interdisciplinary approaches addressing all aspects of speech science and technology, ranging from basic theories to advanced applications.

Recently, deep learning methods have been increasingly applied on spoken language technologies, including signal processing, language understanding and generation, dialogue management, as well as joint optimisations of these (end-to-end learning). However, such methods still have limitations and it is not yet clear that deep learning and joint optimisation is the key to the future. Encompassing the current deep learning trends and traditional knowledge-based methods, SLT's 2020 main theme will be around "Spoken language technologies: deep learning and beyond".

IEEE Signal Processing Society

Reconnaissance de formes et traitement d'image, vision par ordinateur,    Acoustique et vibrations

IEEE Signal Processing Society

Reconnaissance de formes et traitement d'image, vision par ordinateur,    Acoustique et vibrations