The ability to describe the order of events is crucial for effective communication. It is used to describe causality, to plan and to relay stories.
Event ordering can be thought of in terms of binary temporal relations which hold between event pairs or pairs of times and events. Complex event structures can be modelled as compositions of these pairs.
Temporal relations can be expressed linguistically in a variety of ways.
For example, one may use tense to describe the relation between the time of speaking and other events, or use a temporal conjunction to temporal situate an event relative to time.
In the area of automatic temporal information extraction, determining the type of temporal relation between a given pair of times or events is currently the hardest task.
Very sophisticated approaches have yielded only small improvements over initial attempts.
Rather than develop a generic approach to event ordering through relation typing, a failure analysis informs grouping and segmentation of these temporal relations according to the type of information that can be used to temporally relate them. Two major sources of information are identified that provide typing information for two segments: relations explicitly described by a signal word, and relations involving a shift of tense and aspect.
Following this, we investigate automatic temporal relation typing in both these segments, presenting results, introducing new methods and a generating set of new language resources.
