Classifying Temporal Relations Between Events

摘要: This paper describes a fully automatic two-stage machine learning architecture that learns temporal relations between pairs of events. The first stage the attributes single event descriptions, such as tense, grammatical aspect, and aspectual class. These imperfect guesses, combined with other linguistic features, are then used in second to classify relationship two We present both an analysis our new features results on TimeBank Corpus is 3% higher than previous work perfect human tagged features.