Work on the production of texts in English describing instances of a particular event type from multiple news sources will be described. A system has been developed which extracts events , such as meetings, from texts in English, Russian, Spanish, and Japanese. The extraction is currently carried out using only ontological information. The results of a set of such extractions were combined to produce a table of event instances, date stamped, with links back to the original documents. The original documents can then be summarized and translated by the system on demand. By using techniques from information retrieval, information extraction, summarization, and machine translation, in a multi-lingual environment, new documents can be produced which provide "at a glance" access to news on events from multiple sources. The paper concludes with a discussion of the key resources which need to be developed to enhance the accuracy and coverage of the techniques used in our experiment.
展开▼
