Event recognition based on time series characteristics

Event recognition and temporal information analysis are important subtasks in information extraction (IE). In this paper, event recognition based on time series characteristics is proposed. In the pipeline of event recognition, trigger word table is extracted from training corpus and extended based on the field and thesaurus, which is regarded as a priori knowledge. Then event recognition is carried out using trigger words and support vector machine (SVM). Temporal expressions are normalized primarily when recognizing event time. Especially, keywords on time and their priorities are taken into account. Finally, events are sorted by time series characteristics. The results show that methods proposed in this paper are valid and effective.