Télécharger la liste

Description du projet

Presage (formerly known as Soothsayer) is an intelligent predictive text entry platform. It exploits redundant information embedded in natural languages to generate predictions. Its modular and pluggable architecture allows its language model to be extended and customized to utilize statistical, syntactic, and semantic information sources.

Système requise

System requirement is not defined
Information regarding Project Releases and Project Resources. Note that the information here is a quote from Freecode.com page, and the downloads themselves may not be hosted on OSDN.

2009-11-01 23:17 Retour à la liste release
0.7.3

Cette version inclut le plugin prédictive de nouveaux ARPA, qui permet l'utilisation du langage de modélisation statistique des données dans le N ARPA-format gramme. Chaque N-gram est stockée avec sa probabilité log promos Katz et son poids de ralentissement. Les probabilités sont estimées en appliquant Katz Backoff de lissage pour le maximum de vraisemblance des estimations basées sur les données des comptes n-gramme. Cette version offre également un modèle de langage vaste généré à partir du British National Corpus (BNC) contenant unigrams 20001, 517537 bigrammes et 1648226 trigrammes, calculé en utilisant un lissé trigramme Katz Backoff modèle.
This version includes the new predictive ARPA plugin, which enables the use of statistical language modelling data in the ARPA N-gram format. Each N-gram is stored with its discounted log probability and its Katz backoff weight. Probabilities are estimated by applying Katz backoff smoothing to the maximum likelihood estimates based on n-gram counts data. This version also provides an extensive language model generated from the British National Corpus (BNC) containing 20,001 unigrams, 517,537 bigrams, and 1,648,226 trigrams, computed using a smoothed Katz backoff trigram model.

Project Resources