Paper: MultiDPS – A multilingual Discourse Processing System

ACL ID C14-2010
Title MultiDPS – A multilingual Discourse Processing System
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2014

1This paper presents an adaptable online Multilingual Discourse Processing System (Mul- tiDPS), composed of four natural language processing tools: named entity recognizer, anapho- ra resolver, clause splitter and a discourse parser. This NLP Meta System allows any user to run it on the web or via web services and, if necessary, to build its own processing chain, by incorporating knowledge or resources for each tool for the desired language. In this paper is presented a brief description for each independent module, and a case study in which the sys- tem is adapted to five different languages for creating a multilingual summarization system.