Abstract
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 on data across large geographical spaces (total projected area 20,600 km2), as well as temporal trends across longer time frames (ranging from one week up to a year). We identify challenges at all stages of the classical NLG pipeline.
Original language | English |
---|---|
Title of host publication | INLG 2012 - Proceedings of the 7th International Natural Language Generation Conference |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 17-21 |
Number of pages | 5 |
ISBN (Electronic) | 9781937284237 |
Publication status | Published - 2012 |
Event | 7th International Natural Language Generation Conference, INLG 2012 - Utica, United States Duration: 30 May 2012 → 1 Jun 2012 |
Conference
Conference | 7th International Natural Language Generation Conference, INLG 2012 |
---|---|
Country/Territory | United States |
City | Utica |
Period | 30/05/12 → 1/06/12 |
Bibliographical note
Publisher Copyright:© 2012 The Association for Computational Linguistics.