Abstract
One of the main challenges in automatically generating textual weather forecasts is choosing appropriate English words to communicate numeric weather data. A corpus-based analysis of how humans write forecasts showed that there were major differences in how individual writers performed this task, that is, in how they translated data into words. These differences included both different preferences between potential near-synonyms that could be used to express information, and also differences in the meanings that individual writers associated with specific words. Because we thought these differences could confuse readers, we built our SUMTIME-MOUSAM weather-forecast generator to use consistent data-to-word rules, which avoided words which were only used by a few people, and words which were interpreted differently by different people. An evaluation by forecast users suggested that they preferred SUMTIME-MOUSAM's texts to human-generated texts, in part because of better word choice; this may be the first time that an evaluation has shown that NLG texts are better than human-authored texts. (c) 2005 Elsevier B.V. All rights reserved.
Original language | English |
---|---|
Pages (from-to) | 137-169 |
Number of pages | 32 |
Journal | Artificial Intelligence |
Volume | 167 |
DOIs | |
Publication status | Published - Sept 2005 |
Keywords
- natural language processing
- natural language generation
- language and the word
- information presentation
- weather forecasts
- lexical choice
- idiolect
- SEMANTICS
Fingerprint
Dive into the research topics of 'Choosing Words in Computer-Generated Weather Forecasts'. Together they form a unique fingerprint.Impacts
-
Data2Text
Ehud Reiter (Coordinator), Gowri Sripada (Coordinator), Jim Hunter (Coordinator) & Ross John Turner (Coordinator)
Impact
-
Mainstream communication of big data using natural language generation (NLG)
Ehud Reiter (Coordinator) & Gowri Sripada (Coordinator)
Impact: Economic and/or Commercial
-
Promoting the Public Understanding of Artificial Intelligence
Graeme Ritchie (Coordinator), Kees Jacobus Van Deemter (Coordinator), Ehud Reiter (Coordinator) & Gowri Sripada (Coordinator)
Impact