Amplifying the Range of News Stories with Creativity: Methods and their Evaluation, in Portuguese

Rui Mendes, Hugo Gonçalo Oliveira


Abstract
Headlines are key for attracting people to a story, but writing appealing headlines requires time and talent. This work aims to automate the production of creative short texts (e.g., news headlines) for an input context (e.g., existing headlines), thus amplifying its range. Well-known expressions (e.g., proverbs, movie titles), which typically include word-play and resort to figurative language, are used as a starting point. Given an input text, they can be recommended by exploiting Semantic Textual Similarity (STS) techniques, or adapted towards higher relatedness. For the latter, three methods that exploit static word embeddings are proposed. Experimentation in Portuguese lead to some conclusions, based on human opinions: STS methods that look exclusively at the surface text, recommend more related expressions; resulting expressions are somewhat related to the input, but adaptation leads to higher relatedness and novelty; humour can be an indirect consequence, but most outputs are not funny.
Anthology ID:
2020.inlg-1.32
Volume:
Proceedings of the 13th International Conference on Natural Language Generation
Month:
December
Year:
2020
Address:
Dublin, Ireland
Editors:
Brian Davis, Yvette Graham, John Kelleher, Yaji Sripada
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
252–262
Language:
URL:
https://aclanthology.org/2020.inlg-1.32
DOI:
10.18653/v1/2020.inlg-1.32
Bibkey:
Cite (ACL):
Rui Mendes and Hugo Gonçalo Oliveira. 2020. Amplifying the Range of News Stories with Creativity: Methods and their Evaluation, in Portuguese. In Proceedings of the 13th International Conference on Natural Language Generation, pages 252–262, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Amplifying the Range of News Stories with Creativity: Methods and their Evaluation, in Portuguese (Mendes & Gonçalo Oliveira, INLG 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.inlg-1.32.pdf