Improving Text Generation Through Introducing Coherence Metrics

Text-based interaction with the use of mobile devices is now ubiquitous, its main outlets being social networks, messengers, email conversations, virtual assistants, accessibility applications, etc. Its status implies the need to facilitate text input by the user and to devise ways to provide verbal...

Full description

Saved in:

Bibliographic Details
Published in:	Cybernetics and systems analysis Vol. 56; no. 1; pp. 13 - 21
Main Authors:	Marchenko, O. O., Radyvonenko, O. S., Ignatova, T. S., Titarchuk, P. V., Zhelezniakov, D. V.
Format:	Journal Article
Language:	English
Published:	New York Springer US 2020 Springer Springer Nature B.V
Subjects:	Analysis Artificial Intelligence Coherence Computational linguistics Control Electronic devices Language processing Mathematics Mathematics and Statistics Mobile devices Natural language interfaces Processor Architectures Social networks Software Engineering/Programming and Operating Systems Systems Theory Virtual networks Weather coherency coherence metrics natural language processing automatic natural language text generation
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Text-based interaction with the use of mobile devices is now ubiquitous, its main outlets being social networks, messengers, email conversations, virtual assistants, accessibility applications, etc. Its status implies the need to facilitate text input by the user and to devise ways to provide verbal feedback. In this paper, we discuss a method of unique text generation for mobile devices and its evaluation methodology as a solution for both stated challenges. We consider the opportunities given by the use of context (location, weather, scheduled events, etc.), limitations in terms of computational resources and data usage, and the inherent subjectivity of creative task assessment given the number of possibly acceptable outputs. The comparison with other text generation approaches shows that the use of coherence metrics helps to achieve higher quality in terms of human perception. The Spearman correlation between the values of the proposed coherence metric and the human assessment of text readability is 0.86, which indicates the high quality of the metrics and the effectiveness of the method as a whole.
ISSN:	1060-0396 1573-8337
DOI:	10.1007/s10559-020-00216-x