Treffer: Linguistic-first approach to learning Python for natural language generation: Problem breakdown to pseudocode.

Participants in an elective course on natural language generation developed their ability to program in Python through a linguistic-first, problem-based approach. The primary aim of the course was to create a text generation program, but in doing so, students achieved the secondary aim of increasing their mastery of Python. The course started with a thorough linguistic analysis of the genre of the target language, using both top-down and bottom-up approaches. This served as the basis for the development of a set of guiding principles. These principles were then used to develop pseudocode, which, in turn, served as the foundation for the initial draft of the program. Lessons learned include the importance of aligning aims and assessment criteria, and providing learners with space to struggle. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)