The Internet constitutes a potential huge store of parallel text that may be collected to be exploited by many applications such as multilingual information retrieval, machine tran...
This paper describes an advanced system for multilingual text classification adaptable to different user needs. The system has been initially developed as an applied research proje...
Fabio Ciravegna, Alberto Lavelli, Nadia Mana, Joha...
We present a new method for detecting and disambiguating named entities in open domain text. A disambiguation SVM kernel is trained to exploit the high coverage and rich structure...
We address the problem of improving the efficiency of natural language text input under degraded conditions (for instance, on PDAs or cell phones or by disabled users) by taking a...
Knowledge-based natural language processing systems learn by reading, i.e., they process texts to extract knowledge. The performance of these systems crucially depends on knowledg...