Acrostic Poem Generation

Rajat Agarwal, Katharina Kann


Abstract
We propose a new task in the area of computational creativity: acrostic poem generation in English. Acrostic poems are poems that contain a hidden message; typically, the first letter of each line spells out a word or short phrase. We define the task as a generation task with multiple constraints: given an input word, 1) the initial letters of each line should spell out the provided word, 2) the poem’s semantics should also relate to it, and 3) the poem should conform to a rhyming scheme. We further provide a baseline model for the task, which consists of a conditional neural language model in combination with a neural rhyming model. Since no dedicated datasets for acrostic poem generation exist, we create training data for our task by first training a separate topic prediction model on a small set of topic-annotated poems and then predicting topics for additional poems. Our experiments show that the acrostic poems generated by our baseline are received well by humans and do not lose much quality due to the additional constraints. Last, we confirm that poems generated by our model are indeed closely related to the provided prompts, and that pretraining on Wikipedia can boost performance.
Anthology ID:
2020.emnlp-main.94
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1230–1240
Language:
URL:
https://aclanthology.org/2020.emnlp-main.94
DOI:
10.18653/v1/2020.emnlp-main.94
Bibkey:
Cite (ACL):
Rajat Agarwal and Katharina Kann. 2020. Acrostic Poem Generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1230–1240, Online. Association for Computational Linguistics.
Cite (Informal):
Acrostic Poem Generation (Agarwal & Kann, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.94.pdf
Video:
 https://slideslive.com/38938805