Paper: Event Extraction for Balkan Languages

ACL ID E14-2017
Title Event Extraction for Balkan Languages
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014

We describe a system for real-time detec- tion of security and crisis events from on- line news in three Balkan languages: Turk- ish, Romanian and Bulgarian. The system classifies the events according to a fine- grained event type set. It extracts struc- tured information from news reports, by using a blend of keyword matching and finite-state grammars for entity recogni- tion. We apply a multilingual methodol- ogy for the development of the system?s language resources, based on adaptation of language-independent grammars and on weakly-supervised learning of lexical re- sources. Detailed performance evaluation proves that the approach is effective in de- veloping real-world semantic processing applications for relatively less-resourced languages.