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

Dimitra Gkatzia, Helen Hastie, Oliver Lemon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

A Natural Language Generation (NLG) system is able to generate text from non-linguistic 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.
Original languageEnglish
Title of host publicationProceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers
PublisherAssociation for Computational Linguistics
Pages210-214
Number of pages5
ISBN (Print)9781937284787
DOIs
Publication statusPublished - 2014
Event14th Conference of the European Chapter of the Association for Computational Linguistics - Chalmers University, Gothenburg, Sweden
Duration: 26 Apr 201430 Apr 2014
http://eacl2014.org/

Conference

Conference14th Conference of the European Chapter of the Association for Computational Linguistics
Abbreviated titleEACL 2014
Country/TerritorySweden
CityGothenburg
Period26/04/1430/04/14
Internet address

Fingerprint

Dive into the research topics of 'Finding middle ground? Multi-objective Natural Language Generation from time-series data'. Together they form a unique fingerprint.

Cite this