Generating Weather Forecast Texts with Case Based Reasoning

Several techniques have been used to generate weather forecast texts. In this paper, case based reasoning (CBR) is proposed for weather forecast text generation because similar weather conditions occur over time and should have similar forecast texts. CBR-METEO, a system for generating weather forecast texts was developed using a generic framework (jCOLIBRI) which provides modules for the standard components of the CBR architecture. The advantage in a CBR approach is that systems can be built in minimal time with far less human effort after initial consultation with experts. The approach depends heavily on the goodness of the retrieval and revision components of the CBR process. We evaluated CBRMETEO with NIST, an automated metric which has been shown to correlate well with human judgements for this domain. The system shows comparable performance with other NLG systems that perform the same task.

[1]  Ehud Reiter,et al.  SumTime-Mousam: Configurable marine weather forecast generator , 2003 .

[2]  Ion Androutsopoulos,et al.  Learning to Order Facts for Discourse Planning in Natural Language Generation , 2003, ENLG@EACL.

[3]  Susan Craw,et al.  Learning adaptation knowledge to improve case-based reasoning , 2006, Artif. Intell..

[4]  Pablo Gervás.  Automatic Generation of Poetry using a CBR Approach , 2002 .

[5]  Alain Polguère,et al.  Bilingual Generation of Weather Forecasts in an Operations Environment , 1990, COLING.

[6]  E. Reiter,et al.  Acquiring Correct Knowledge for Natural Language Generation , 2011, J. Artif. Intell. Res..

[7]  Anja Belz,et al.  System Building Cost vs. Output Quality in Data-to-Text Generation , 2009, ENLG.

[8]  Anja Belz,et al.  Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models , 2008, Natural Language Engineering.

[9]  José Coch.  System Demonstration Interactive Generation And Knowledge Administration In Multimeteo , 1998, INLG.

[10]  George R. Doddington,et al.  Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics , 2002 .

[11]  Robert Dale,et al.  Building applied natural language generation systems , 1997, Natural Language Engineering.

[12]  Raquel Hervás,et al.  Story plot generation based on CBR , 2004, Knowl. Based Syst..

[13]  Robert Rubinoff,et al.  Integrating Text planning and linguistic choice without abandoning modularity: the IGEN generator , 2000, CL.

[14]  Anja Belz.  Prodigy-METEO : Pre-Alpha Release Notes ( Nov 2009 ) , 2009 .

[15]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[16]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[17]  Harry R. Glahn.  computer-produced worded forecasts , 1970 .

[18]  Alain Polguère,et al.  Synthesizing Weather Forecasts from Formatted Data , 1986, COLING.

[19]  Richard I. Kittredge,et al.  Using natural-language processing to produce weather forecasts , 1994, IEEE Expert.

[20]  Pedro A. González-Calero,et al.  Building CBR systems with jcolibri , 2007, Sci. Comput. Program..

[21]  Anja Belz,et al.  Comparing Automatic and Human Evaluation of NLG Systems , 2006, EACL.

[22]  Christer Johansson,et al.  Deep Comprehension, Generation And Translation Of Weather Forecasts (Weathra) , 1992, COLING.

[23]  Somayajulu Sripada,et al.  SUMTIME-METEO: Parallel Corpus of Naturally Occurring Forecast Texts and Weather Data , 2008 .

[24]  Eduard H. Hovy,et al.  Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.