This paper argues that simplifying the interoperability of different NLP tools performing similar but also complementary tasks will facilitate the comparability of results and the creation of sophisticated NLP applications. It presents the NLP Interchange Format (NIF). NIF is based on a Linked Data enabled URI scheme for identifying elements in (hyper-)texts and an ontology for describing common NLP terms and concepts. In contrast to more centralized solutions such as UIMA and GATE, NIF enables the creation of heterogeneous, distributed and loosely coupled NLP applications, which use the Web as an integration platform. Also available as PDF: http://videolectures.net/site/normal_dl/tag=817841/iswc2013_hellmann_linked_data_01.pdf
URL: http://videolectures.net/iswc2013_hellmann_linked_data/
Keywords: Linked Data, HTTP URIs, International Tag Set (IST) 2.0, Ontology, Web Ontology Language (OWL), Natural Language Processing
Author: Hellmann, Sebastian
Publisher: videolectures.net
Date created: 2013-11-28 05:00:00.000
Language: http://id.loc.gov/vocabulary/iso639-2/eng
Time required: P15M
Educational use: professionalDevelopment
Educational audience: professional
Interactivity type: expositive