engleski

Event and Temporal Relation Extraction from Croatian Newspaper Texts

Event extraction and temporal relation extraction are the subjects of extensive research, which has been additionally motivated by focused evaluation exercises such as TempEval. In this paper we present the work on supervised event and temporal relation extraction from Croatian newspaper texts. Taking into account the limited availability of linguistic tools for Croatian, we focus our research around simple lexical features. We manually annotated a newspaper corpus or events and temporal relations in Croatian according to the TimeML and TimeBank guidelines. Experimental evaluation yielded promising results: F1 scores of up to 77% for event identification, 48% for event classification, and 51% for temporal relation classification.

Event Extraction; Temporal Relation Extraction

nije evidentirano