Domain-independent shallow sentence ordering

Abstract

We present a shallow approach to the sentence ordering problem. The employed features are based on discourse entities, shallow syntactic analysis, and temporal precedence relations retrieved from VerbOcean. We show that these relatively simple features perform well in a machine learning algorithm on datasets containing sequences of events, and that the resulting models achieve optimal performance with small amounts of training data. The model does not yet perform well on datasets describing the consequences of events, such as the destructions after an earthquake.