On Named Entity Recognition in Targeted Twitter Streams in Polish.
Jakub Piskorski, Maud Ehrmann · Meeting of the Association for Computational Linguistics · 2013
This paper reports on some experiments aiming at tuning a rule-based NER system designed for detecting names in Polish online news to the processing of targeted Twitter streams. In particular, one explores whether the performance of the baseline NER system can be improved through the incremental application of knowledge-poor methods for name matching and guessing. We study various settings and combinations of the methods and present evaluation results on five corpora gathered from Twitter, centred around major events and known individuals.