Automatic Generation of Literary Sentences
DOI:
https://doi.org/10.21814/lm.12.1.308Keywords:
Literary Corpora, Automatic Sentence Generation, Markov Chains, Deep Learning, Canned TextAbstract
In this article, we regard the task of automatic generation of literary sentences, which is an important topic in the area of Computational Creativity. We propose three generative models mainly based on statistical algorithms and shallow parsing. The generated texts were evaluated by seven persons according to four criteria: grammar, coherence, context related, and an adaptation of the Turing test. We present preliminary results of their implementations that are quite encouraging.
References
Downloads
Published
2020-06-25
Issue
Section
Research Articles
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).
How to Cite
Automatic Generation of Literary Sentences. (2020). Linguamática, 12(1), 15-30. https://doi.org/10.21814/lm.12.1.308
