The paper “An Analysis of Causality between Events and its Relation to Temporal Information” by Paramita Mirza and Sara Tonelli has been accepted for oral presentation at the 25th International Conference on Computational Linguistics (Coling 2014).


In this work we present an annotation framework to capture causality between events, inspired by TimeML, and a language resource covering both temporal and causal relations. This data set is then used to build an automatic extraction system for causal signals and causal links between given event pairs. The evaluation and analysis of the system’s performance provides an insight into explicit causality in text and the connection between temporal and causal relations.