Describing golf shots using Natural LanguageGenerationAn: An investigation of a suitable method for implementing a Natural LanguageGeneration system with the aim of being a useful resource for golfers
Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Natural Language Generation, NLG, is the translation ofraw data into legible and understandable text. It is currently being used in a variety of ways ranging from weatherforecasts to directions given by Google Maps. External NLG libraries are available for several programming languages, allowing more focus on the determining what would be included in the text generated.This report aims to investigate a suitable method of building an NLG system to be used with data provided by the Protracer software with the intent to provide golferswith text-based feedback of their game. Possible methods have been narrowed down to three approaches. The firstis simply outputting random feedback to the golfer with generic words and hope for the best. The second is usinga machine learning technique that takes shot parametersalong with a human interpretation of that shot. From this, the algorithm would acquire information about what buildsup a specific shot. Finally, the last method is using shotparameters along with human interpretation to construct an algorithm with observed threshold values to determine the shot type. Ultimately, the system constructed with the help of thereport was effective in classifying and describing golf ball trajectories. The difference between human interpretation and that of the system was negligible as the line between the classifications of a golf shot is very thin.
Place, publisher, year, edition, pages
IdentifiersURN: urn:nbn:se:kth:diva-157515OAI: oai:DiVA.org:kth-157515DiVA: diva2:770327