Abstract
The paper investigates how well poetry can be generated to contain a specific sentiment, and whether readers of the poetry experience the intended sentiment. The poetry generator consists of a bi-directional Long Short-Term Memory (LSTM) model, combined with rhyme pair generation, rule-based word prediction methods, and tree search for extending generation possibilities. The LSTM network was trained on a set of English poetry written and published by users on a public website. Human judges evaluated poems generated by the system, both with a positive and negative sentiment. The results indicate that while there are some weaknesses in the system compared to other state-of-the-art solutions, it is fully capable of generating poetry with an inherent sentiment that is perceived by readers.- Anthology ID:
- 2020.icon-main.33
- Volume:
- Proceedings of the 17th International Conference on Natural Language Processing (ICON)
- Month:
- December
- Year:
- 2020
- Address:
- Indian Institute of Technology Patna, Patna, India
- Editors:
- Pushpak Bhattacharyya, Dipti Misra Sharma, Rajeev Sangal
- Venue:
- ICON
- SIG:
- Publisher:
- NLP Association of India (NLPAI)
- Note:
- Pages:
- 246–256
- Language:
- URL:
- https://aclanthology.org/2020.icon-main.33
- DOI:
- Cite (ACL):
- Kasper Aalberg Røstvold and Björn Gambäck. 2020. Sentimental Poetry Generation. In Proceedings of the 17th International Conference on Natural Language Processing (ICON), pages 246–256, Indian Institute of Technology Patna, Patna, India. NLP Association of India (NLPAI).
- Cite (Informal):
- Sentimental Poetry Generation (Røstvold & Gambäck, ICON 2020)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2020.icon-main.33.pdf