Automated Language Processing with Applications for Cultural Heritage Appreciation

Researchers from Israel:

Ido Dagan, Nurit Melnik, Danny Shacham, Idan Szpektor, Shuly Wintner

Researchers from Italy:

Bonaventura Coppola, Christian Girardi, Alfio Gliozzo, Milen Kouylekov, Alberto Lavelli, Emanuele Pianta, Lorenzo Romano, Carlo Strapparava, Hristo Tanev

The project is divided into two main components:

• Knowledge Learning Approaches for Natural Language Processing
• The goal of this project is to learn, and eventually utilize, knowledge about the variability of semantic expression in natural language. This goal must be addressed by practically all language understanding applications, such as Question Answering (QA), Information Extraction (IE), Information Retrieval (IR), text summarization and Machine Translation. We focus on developing an unsupervised approach for learning from the web entailment relations between lexical-syntactic templates.
• Showcase for Archaeological Domain
• This project demonstrates the applicability of the Textual Entailment Paradigm for semantic-oriented Information Retrieval, and demonstrates handling of queries that contain specific relations between terms. Furthermore, cross-lingual Information Retrieval capabilities are demonstrated, capitalizing on Hebrew language resources and tools.