Affordable Access

Syntactic properties of natural languages and application to automatic parsing

Sociedad Española para el Procesamiento del Lenguaje Natural
  • Linguistics
  • Logic


sepln09.pdf KNOW: Developing large-scale multilingual technologies for language understanding∗ KNOW: Desarrollo de tecnolog´ıas multilingu¨es a gran escala para la comprensio´n del lenguaje Eneko Agirre German Rigau EHU IxA taldea [email protected] [email protected] Irene Castello´n Laura Alonso UB GRIAL [email protected] [email protected] Lluis Padro´ Montse Cuadros UPC TALP [email protected] [email protected] Salvador Climent Marta Coll-Florit UOC GRIAL [email protected] [email protected] Resumen: El proyecto KNOW pretende an˜adir significado, conocimiento y razon- amiento a las tecnolog´ıas actuales de Procesamiento del Lenguaje Natural. Palabras clave: Procesamiento del Lenguaje Natural, Ana´lisis Sinta´ctico, Inter- pretacio´n Sema´ntica, Adquisicio´n de Conocimiento, Recuperacio´n de Informacio´n Abstract: The KNOW project aims to add meaning, knowledge and reasoning to current Natural Language Processing technologies. Keywords: Natural Language Processing, Syntactic Analysis, Semantic Interpre- tation, Knowledge Acquisition, Information Retrieval 1. General description KNOW aims to add meaning, knowledge and reasoning to current interface technolo- gies. Specifically, KNOW is providing novel natural language interpretation and reason- ing capabilities to current multilingual com- puter applications: full syntactic parsers and semantic interpreters (including word sense disambiguation systems and semantic role labelers) for the languages involved in the project, a common conceptual structure (the Multilingual Central Repository or MCR), and both automatic reasoning and analogy- based inference based on the MCR. KNOW has opened the way for a new generation of broad-coverage unrestricted-domain concept- based language understanding applications. KNOW is demmonstrating the feasibility of these technologies in two applications linked to the project EPOs: Cross Lingual Infor- mation Retrieval and Question/Answering on two multi-modal dat

There are no comments yet on this publication. Be the first to share your thoughts.


Seen <100 times