Abstract
This paper addresses author-stylized text generation. Using a version of a language model with extended phonetic and semantic embeddings for poetry generation we show that phonetics has comparable contribution to the overall model performance as the information on the target author. Phonetic information is shown to be important for English and Russian language. Humans tend to attribute machine generated texts to the target author.- Anthology ID:
- W18-5813
- Volume:
- Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Sandra Kuebler, Garrett Nicolai
- Venue:
- EMNLP
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 117–124
- Language:
- URL:
- https://aclanthology.org/W18-5813
- DOI:
- 10.18653/v1/W18-5813
- Cite (ACL):
- Aleksey Tikhonov and Ivan P. Yamshchikov. 2018. Sounds Wilde. Phonetically Extended Embeddings for Author-Stylized Poetry Generation. In Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 117–124, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Sounds Wilde. Phonetically Extended Embeddings for Author-Stylized Poetry Generation (Tikhonov & Yamshchikov, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/W18-5813.pdf