Marchenko O. O., Radyvonenko O. S., Ignatova T. S., Titarchuk P. V., Zhelezniakov D. V.
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 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. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

Keywords: automatic natural language text generation, coherence metrics, coherency, natural language processing, Computer science, Cybernetics, Coherence metric, coherency, Computational resources, Human perception, NAtural language processing, Natural language text, Spearman correlation, Virtual assistants, Natural language processing systems

PDF

Cite:
Marchenko, Radyvonenko, Ignatova, Titarchuk, Zhelezniakov. (2020). Improving text generation through introducing coherence metrics. Cybernetics and Systems Analysis, 56 (1), 16–25. doi: https://doi.org/10.1007/s10559-020-00216-x http://jnas.nbuv.gov.ua/article/UJRN-0001074959