| 1 |
Syllable Neural Language Models for English Poem Generation
|
|
|
|
Abstract:
Automatic Poem Generation is an ambitious Natural Language Generation (NLG) problem. Indeed, models have to replicate the precise structure of poems, rhymes, meters, while producing creative and emotional verses. Furthermore, the lack of abundant poetic corpora, especially for ancient poetry, is a serious limitation for the development of strong poem generators. In this paper, we propose a syllable neural language model to the case of English language, focusing on the generation of verses with the style of a target author: William Wordsworth. To alleviate the problem of limited available data, we exploit transfer learning. Furthermore, we bias the generation of verses according to a combination of different scoring functions based on meter, style and gram-mar in order to select lines more compliant with the author’s characteristics. The results of both quantitative and human evaluations shows the effectiveness of our approach. In particular, human judges struggle to recognize real verses from the generated ones.
|
|
Keyword:
PE English; QA75 Electronic computers. Computer science
|
|
URL: https://openaccess.city.ac.uk/id/eprint/26230/1/ICCC_2021.pdf
https://openaccess.city.ac.uk/id/eprint/26230/
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Gene Expression Imputation Across Multiple Tissue Types Provides Insight Into the Genetic Architecture of Frontotemporal Dementia and Its Clinical Subtypes
|
|
|
|
BASE
|
|
Show details
|
|
|
| 3 |
The CARMENES search for exoplanets around M dwarfs First visual-channel radial-velocity measurements and orbital parameter updates of seven M-dwarf planetary systems
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Computational models of learning and beyond: Symmetries of associative learning
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
