Acrostic Poem Generation

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 1230–1240, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 1230 Acrostic Poem Generation Rajat Agarwal New York University rajat.agarwal@nyu.edu Katharina Kann University of Colorado Boulder katharina.kann@colorado.edu Abstract We propose a new task in the area of compu- tational 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 con- straints. Last, we confirm that poems gener- ated by our model are indeed closely related to the provided prompts, and that pretraining on Wikipedia can boost performance. 1 Introduction Poetry, derived from the Greek word poiesis (”making”), is the art of combining rhythmic and aesthetic properties of a language to convey a spe- cific message. Its creation is a manifestation of creativity, and, as such, hard to automate. How- ever, since the development of creative machines is a crucial step towards real artificial intelligence, automatic poem generation is an important task at the intersection of computational creativity and nat- ural language generation, and earliest attempts date back several decades; see Gonc¸alo Oliveira (2017) for an overview. Figure 1: An acrostic poem generated by our proposed baseline model for the word poet. With this paper, we add a new task to this re- search area: acrostic poem generation in English. Acrostic poems, or simply acrostics, are a special type of poetry, in which typically the first letter of each line spells out a word or message, as in the example in Figure 1. While this is the only for- mal characteristic of an acrostic, we here define the task of acrostic poem generation as generating po- ems such that, additionally, poems should also both rhyme and relate to the topic of their hidden word, e.g., the content of the poem in Figure 1 should be related to the word ”poet”. As far as meter is concerned, we are interested in free verse poems. Acrostic poem generation, as we define it, is a chal- lenging constrained generation task with multiple constraints: semantic ones (the content of the poem should follow a given topic), and structural ones …

Content truncated to 500 words