Multi-adaptive Natural Language Generation using Principal Component Regression

Gkatzia, Dimitra; Hastie, Helen; Lemon, Oliver

Abstract

We present FeedbackGen, a system that uses a multi-adaptive approach to Natural Language Generation. With the term 'multi-adaptive', we refer to a system that is able to adapt its content to different user groups simultaneously, in our case adapting to both lecturers and students. We present a novel approach to student feedback generation, which simultaneously takes into account the preferences of lecturers and students when determining the content to be conveyed in a feedback summary. In this framework, we utilise knowledge derived from ratings on feedback summaries by extracting the most relevant features using Principal Component Regression (PCR) analysis. We then model a reward function that is used for training a Reinforcement Learning agent. Our results with students suggest that, from the students' perspective , such an approach can generate more preferable summaries than a purely lecturer-adapted approach.

Citation

Gkatzia, D., Hastie, H., & Lemon, O. (2014, June). Multi-adaptive Natural Language Generation using Principal Component Regression. Presented at International Natural Language Generation Conference (INLG)

• Conference Name: International Natural Language Generation Conference (INLG)
• Start Date: Jun 19, 2014
• End Date: Jun 21, 2014
• Acceptance Date: Apr 30, 2014
• Publication Date: 2014-06
• Deposit Date: Dec 14, 2017
• Publicly Available Date: Dec 15, 2017
• Journal: Proceedings of the 8th International Natural Language Generation Conference
• Pages: 138-142
• Book Title: Proceedings of the 8th International Natural Language Generation Conference
• Chapter Number: N/A
• ISBN: 978-1-941643-22-8
• Keywords: FeedbackGen, Natural Language Generation, Principal Component Regression (PCR),
• Public URL: http://researchrepository.napier.ac.uk/Output/929975
• Contract Date: Dec 14, 2017