Paramita Mirza (Max-Planck-Institut für Informatik, Saarbrücken),
Jun 27, 2017,
Structured information resulting from temporal information processing is crucial for a variety of natural language processing tasks, for instance to generate timeline summarization of events from news documents, or to answer temporal/causal-related questions about events.
In this talk, automatic extraction of temporal information from texts will be discussed, with more emphasis on temporal ordering and causal relations, and their interaction based on the presumption about event precedence in causality, that causing events must happened BEFORE resulting events. Several resources and techniques to improve temporal/causal relation extraction systems will also be discussed, including word embeddings and common sense knowledge.