Personality-dependent sentence rewriting
Abstract
Natural Language Generation (NLG) systems are central to the development of psychologically plausible human-computer communication that does not rely on canned text, and which makes use of a wide range of strategies to model some stylistic variation. Among these, the use of computational models of human personality has emerged as a popular alternative in the field. In this context, the present work presents a text-to-text (or sentential rewriting) GLN model for Portuguese that takes into account, in addition to the sentence to be rewritten, information about the personality of a target speaker of interest. More specifically, the model transforms the input sentence into another one in which certain lexical forms are replaced by terms more suited to a certain personality type. Results suggest that personality-based generation produces sentences that are closer to those produced by a human speaker with those personality traits than what would be possible without access to this information, thus paving the way for future studies of speaker-dependent natural language generation in Portuguese.
Copyright (c) 2020 Georges Basile Stavracas Neto, Ivandré Paraboni
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
