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.
The semantics of UML [3] is for a large part given in English. The drawback of Eng-lish is its ambiguity, which makes it unclear and ambiguous. But the benefits of Eng-lish are its power and flexibility, which allow it to deal with a slightly inconsistent ...
Preparation of a lexicon for speech recognition systems can be a significant effort in languages where the written form is not exactly phonetic. On the other hand, in languages where the written form is quite phonetic, some common words are often mispronou ...
This paper investigates the automatic detection of English spoken terms in a multi-language scenario over real lecture recordings. Spoken Term Detection (STD) is based on an LVCSR where the output is represented in the form of word lattices. The lattices a ...
Tome 1 : Dans quelle mesure les projets réalisés par l'agence Herzog et de Meuron dans les années 1990 et 2000 constituent-ils une innovation en termes de langage architectural ? Qu'impliquent-ils par rapport au statut de l'édifice contemporain comme progr ...
École Normale Supérieure d'Architecture de Paris-Belleville (ENSAPB)2007
This paper gives a detailed description of the ACT (Accuracy of Connective Translation) metric, a reference-based metric that assesses only connective translations. ACT relies on automatic word-level alignment (using GIZA++) between a source sentence and r ...
In a bilingual paper entitled 'Bibliometrics as weapons of mass citation - La bibliometrie comme arme de citation massive',([1]) recently translated into English,([2]) we have argued that the current fashion of ranking people, papers and journals is anythi ...
This paper investigates the automatic detection of English spoken terms in a multi-language scenario over real lecture recordings. Spoken Term Detection (STD) is based on an LVCSR where the output is represented in the form of word lattices. The lattices a ...
The equivalent English title: "Design of Custom Networks-on-Chip with Physical Layout Information" Abstract translated into English: Due to the growing demand of communication between processors and memory devices in Systems-on-Chip (SoCs), recently the ne ...