作者: Nava Tintarev , Somayajulu Sripada , Elizabeth Tait , Chris Mellish , Rene Van Der Wal
DOI:
关键词: Data science 、 Ranging 、 Pipeline (software) 、 Computer science 、 Work (electrical) 、 Natural language generation 、 Nature Conservation
摘要: We describe preliminary work on generating contextualized text for nature conservation volunteers. This Natural Language Generation (NLG) differs from other ways of describing spatio-temporal data, in that it deals with abstractions data across large geographical spaces (total projected area 20,600 km2), as well temporal trends longer time frames (ranging one week up to a year). identify challenges at all stages the classical NLG pipeline.