Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models

Two important recent trends in natural language generation are (i) probabilistic techniques and (ii) comprehensive approaches that move away from traditional strictly modular and sequential models. This paper reports experiments in which pcru – a generation framework that combines probabilistic gene...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Natural language engineering Ročník 14; číslo 4; s. 431 - 455
Hlavný autor: BELZ, ANJA
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cambridge, UK Cambridge University Press 01.10.2008
Predmet:
Automatic Text Generation
Computational Linguistics
Computer Modeling and Simulation
Decision making
Experiments
Forecasting
Language
Natural language
Natural Language Generation
Natural Language Processing
Probability
Statistical Analysis
Statistical methods
Subject specialists
Trends
Weather
Weather forecasting
ISSN:1351-3249, 1469-8110
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Two important recent trends in natural language generation are (i) probabilistic techniques and (ii) comprehensive approaches that move away from traditional strictly modular and sequential models. This paper reports experiments in which pcru – a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space – was used to semi-automatically create five different versions of a weather forecast generator. The generators were evaluated in terms of output quality, development time and computational efficiency against (i) human forecasters, (ii) a traditional handcrafted pipelined nlg system and (iii) a halogen-style statistical generator. The most striking result is that despite acquiring all decision-making abilities automatically, the best pcru generators produce outputs of high enough quality to be scored more highly by human judges than forecasts written by experts.
Bibliografia:ArticleID:00466
istex:44D629424E402F90AE4DE5400D2C3B88827F2801
PII:S1351324907004664
ark:/67375/6GQ-7G3PD4KT-7
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1351-3249
1469-8110
DOI:10.1017/S1351324907004664