Finding middle ground? Multi-objective Natural Language Generation from time-series data

Gkatzia, Dimitra; Hastie, Helen; Lemon, Oliver

Abstract

A Natural Language Generation (NLG) system is able to generate text from nonlinguistic data, ideally personalising the content to a user’s specific needs. In some cases, however, there are multiple stakeholders with their own individual goals, needs and preferences. In this paper, we explore the feasibility of combining the preferences of two different user groups, lecturers and students, when generating
summaries in the context of student feedback generation. The preferences of each user group are modelled as a multivariate
optimisation function, therefore the task of generation is seen as a multi-objective (MO) optimisation task, where the two functions are combined into one. This initial study shows that treating the preferences of each user group equally smooths the weights of the MO function, in a way that preferred content of the user groups is
not presented in the generated summary.

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers
• Start Date: Apr 26, 2014
• End Date: Apr 30, 2014
• Acceptance Date: Apr 1, 2014
• Publication Date: 2014
• Deposit Date: Aug 1, 2016
• Publicly Available Date: Feb 21, 2019
• Publisher: Association for Computational Linguistics (ACL)
• Book Title: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers
• ISBN: 978-1-937284-99-2
• DOI: https://doi.org/10.3115/v1/e14-4041
• Keywords: Natural Language Generation (NGL), Lecturers, Students, User Specific Needs,
• Public URL: http://researchrepository.napier.ac.uk/Output/321818
• Contract Date: Feb 21, 2019