Patrick Paroubek

Towards best practice in the development and evaluation of speech recognition components of a spoken language dialog system

This article provides a global overview of the main aspects of current practice in the design, implementation and evaluation of speech recognition components for Spoken Language Dialog Systems (SLDSs), and presents the results of the DISC European project related to speech recognition. DISC and its successor DISC-2 are efforts towards the definition of best practice guidelines for SLDS development and evaluation. SLDSs aim at using natural spoken input for performing an information processing task such as automated standards, call routing or travel planning and reservations. The main functionality of an SLDS are speech recognition, natural language understanding, dialog management, database access and interpretation, response generation and speech synthesis. Speech recognition, which transforms the acoustic signal into a string of words, is a key technology in any SLDS.

PEAS, the first instantiation of a comparative framework for evaluating parsers of French

This paper presents PEAS, the first comparative evaluation framework for parsers of French whose annotation formalism allows the annotation of both constituents and functional relations. A test corpus containing an assortment of different text types has been built and part of it has been manually annotated. Precision/Recall and crossing brackets metrics will be adapted to our formalism and applied to the parses produced by one parser from academia and another one from industry in order to validate the framework.

Large Scale Production of Syntactic Annotations to Move Forward

This article presents the methodology of the PASSAGE project, aiming at syntactically annotating large corpora by composing annotations. It introduces the annotation format and the syntactic annotation specifications. It describes an important component of the methodolgy, namely an WEB-based evaluation service, deployed in the context of the first PASSAGE parser evaluation campaign.

Human Judgement as a Parameter in Evaluation Campaigns

The relevance of human judgment in an evaluation campaign is illustrated here through the DEFT text mining campaigns. n nIn a first step, testing a topic for a campaign among a limited number of human evaluators informs us about the feasibility of a task. This information comes from the results obtained by the judges, as well as from their personal impressions after passing the test. n nIn a second step, results from individual judges, as well as their pairwise matching, are used in order to adjust the task (choice of a marking scale for DEFT07 and selection of topical categories for DEFT08). n nFinally, the mutual comparison of competitors results, at the end of the evaluation campaign, confirms the choices we made at its starting point, and provides means to redefine the task when we shall launch a future campaign based on the same topic.

The French Language in the European Information Society

With 128 million “native and real speakers” worldwide and an estimate of close to 300 million persons speaking French overall, French appears only as the 16th most spoken native language, but as the 6th most spoken language in the world, after English, Chinese Mandarin, Spanish, Hindi and Russian.

Languages at Risk: A Challenge for Language Technology

We are living a digital revolution that is dramatically impacting communication and society. Recent developments in information and communication technology are sometimes compared to Gutenberg’s invention of the printing press. What can this analogy tell us about the future of the European information society and our languages in particular?

Les Langues En Danger: Un Défi Pour Les Technologies De La Langue

Nous vivons une revolution numerique qui a un impact fort sur la communication et la societe. Les developpements recents des technologies de communication numerique et les reseaux sont parfois compares a l’invention par Gutenberg de l’imprimerie.

About Meta-Net

META-NET is a Network of Excellence partially funded by the European Commission. As of March 2012, the network consists of 54 research centres in 33 European countries. META-NET forges META, the Multilingual Europe Technology Alliance, a growing community of language technology professionals and organizations in Europe.

A Propos De Meta-Net

META-NET est un Reseau d’Excellence finance en partie par la Commission europeenne. En mars 2012, le reseau se compose de 54 centres de recherche de 33 pays europeens. META-NET forge META, l’alliance technologique pour une Europe multilingue, communaute grandissante de professionnels et d’organisations travaillant dans le domaine des technologies de la langue en Europe.

Les Technologies De La Langue Pour Le Français

Les technologies de la langue sont des technologies de l’information qui sont specialisees pour traiter le langage humain. Par consequent, ces technologies sont souvent regroupees sous le terme de « technologies du langage humain » . Les technologies de la langue sont un domaine de recherche etabli et reconnu, pour lequel il existe de nombreux textes introductifs.