Generating Weather Forecast Texts with Case Based Reasoning
This work addresses the problem of automating weather forecast text generation for meteorologists or users, but it is incremental as it applies an existing CBR method to this domain.
The paper tackled generating weather forecast texts by proposing a case-based reasoning (CBR) approach, developing the CBR-METEO system using the jCOLIBRI framework, and it shows comparable performance to other natural language generation systems as evaluated with the NIST metric.
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.