The PALIROM project is part of the research and processing of natural languages domain (NLP– Natural Language Processing), a sub domain of Human Language Technologies. The analysis of digital content has two main directions:

  • understanding the language specific text
  • generating text in a specific language

In order to accomplish these, the project’s main objective is to develop a complex application package containing a linguistic knowledge base, the necessary tools for obtaining it and the end-user applications capable of processing and understanding Romanian text and generating messages in Romanian language. Once this knowledge base is created it will serve as a starting point for developing various linguistic applications.

General Objectives

To design and implement an application package for Romanian language analysis and processing, representing the fundaments for future software applications required for achieving a digital economy and unifying the European cultural space.

Specific Objectives:

  • To define the concepts that can help translating the natural language into a computational one
  • To implement the NLP tools for creating, maintaining and using the linguistic knowledge: main framework for Romanian language processing, tools for analyzing the linguistic knowledge base
  • To develop frameworks providing the means for fast development of linguistic applications
  • To develop the linguistic knowledge base (lexicon, morphology, syntax...) required for processing the digital content written in Romanian language
  • To develop end-user applications capable to analyze Romanian language: morphological analyzer, grammar checker, inflection application, lemmatizer, spell checker, all monolingual dictionaries.

Acest site foloseşte cookie-uri. Folosim cookie-uri pentru analiza şi îmbunătăţirea site-ului, personalizarea vizitei, marketing şi reclamă. Prin navigarea pe acest site, vă exprimaţi acordul asupra folosirii cookie-urilor în aceste scopuri. Citiți mai mult.