Impact du degre de supervision sur l'adaptation a un domaine d'un modele de langage a partir du Web
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
Nowadays models, rather than code, become the key artifacts of software development. Consequently, this raises the level of requirements for modeling languages on which modeling practitioners should rely in their work. A minor inconsistency of a modeling l ...
In this work, we propose different strategies for efficiently integrating an automated speech recognition module in the framework of a dialogue-based vocal system. The aim is the study of different ways leading to the improvement of the quality and robustn ...
The context of this paper is Enterprise Architecture (EA). EA is a multi-disciplinary approach that allows dierent specialists to design new business and IT systems and focuses on the integration of these systems. Our group develops a specic EA method that ...
Text embedded in images and videos represents a rich source of information for content-based indexing and retrieval applications. In this paper, we present a new method for localizing and recognizing text in complex images and videos. Text localization is ...
Model-Driven Engineering (MDE) harbors the promise of developing software-based systems with little or no coding. Instead of coding, it is envisioned that software engineers build models that are automatically translated into code. The modeling notation of ...
Model Driven Engineering (MDE) promotes the use of models as primary artefacts of a software development process, as an attempt to handle complexity through abstraction, e.g. to cope with the evolution of execution platforms. MDE follows a stepwise approac ...
Language models for speech recognition are generally trained on text corpora. Since these corpora do not contain the disfluencies found in natural speech, there is a train/test mismatch when these models are applied to conversational speech. In this work w ...
Language models for speech recognition are generally trained on text corpora. Since these corpora do not contain the disfluencies found in natural speech, there is a train/test mismatch when these models are applied to conversational speech. In this work w ...
We present the results of our research that is positioned in the domain of system modeling. In particular, we present an object-oriented paradigm that provides a logically rigorous and complete theoretical base for various existing object-oriented framewor ...
This thesis presents a PhD work on offline cursive handwriting recognition, the automatic transcription of cursive data when only its image is available. Two main approaches were used in the literature to solve the problem. The first one attempts to segmen ...
