engleski

HeidelTime.Hr: Extracting and Normalizing Temporal Expressions in Croatian

Temporal expression extraction and normalization are important for many NLP tasks and have been the topic of extensive research. While the majority of research on temporal expression extraction was performed for English, there has recently also been work on temporal processing for other languages. In this paper, we describe HeidelTime.Hr, the Croatian resources for HeidelTime – a multilingual, cross-domain temporal expression tagger. HeidelTime recognizes temporal expressions in text and normalizes them according to the TIMEX3 annotation standard. We compile WikiWarsHr, a corpus of historical narratives in Croatian manually annotated for temporal expressions. On WikiWarsHr, HeidelTime.Hr achieves results comparable to those originally achieved by HeidelTime on English texts, with F1-scores of 0.93 and 0.86 for expression extraction and normalization, respectively

temporal tagging; information extraction; HeidelTime tagger; Croatian language

nije evidentirano