paper-with-me

Papers

Automating the Detection of Poetic Features: The Limerick as Model Organism

2021-11-01 · EMNLP (LaTeCHCLfL, CLFL, LaTeCH) 2021 11 · Almas Abdibayev, Yohei Igarashi, Allen Riddell, Daniel Rockmore

In this paper we take up the problem of “limerick detection” and describe a system to identify five-line poems as limericks or not. This turns out to be a surprisingly difficult challenge with many subtleties. More precisely, we produce an algorithm which focuses on the structural aspects of the limerick – rhyme scheme and rhythm (i.e., stress patterns) – and when tested on a a culled data set of 98,454 publicly available limericks, our “limerick filter” accepts 67% as limericks. The primary failure of our filter is on the detection of “non-standard” rhymes, which we highlight as an outstanding challenge in computational poetics. Our accent detection algorithm proves to be very robust. Our main contributions are (1) a novel rhyme detection algorithm that works on English words including rare proper nouns and made-up words (and thus, words not in the widely used CMUDict database); (2) a novel rhythm-identifying heuristic that is robust to language noise at moderate levels and comparable in accuracy to state-of-the-art scansion algorithms. As a third significant contribution (3) we make publicly available a large corpus of limericks that includes tags of “limerick” or “not-limerick” as determined by our identification software, thereby providing a benchmark for the community. The poetic tasks that we have identified as challenges for machines suggest that the limerick is a useful “model organism” for the study of machine capabilities in poetry and more broadly literature and language. We include a list of open challenges as well. Generally, we anticipate that this work will provide useful material and benchmarks for future explorations in the field.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Rhythm

Similar Papers 제목 키워드 기반

BPoMP: The Benchmark of Poetic Minimal Pairs – Limericks, Rhyme, and Narrative Coherence

2021-09-01 · RANLP 2021 9 · Almas Abdibayev, Allen Riddell, Daniel Rockmore

We adapt BLiMP (Benchmark of Linguistic Minimal Pairs) language model evaluation framework to the context of poetry, introducing the first of a series of tasks titled Benchmark of Poetic Minimal Pairs (BPoMP). The tasks …

Language Model EvaluationLanguage Modelling

There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It

2021-03-05 · Jianyou Wang, Xiaoxuan Zhang, Yuren Zhou, Christopher Suh 외

Limerick generation exemplifies some of the most difficult challenges faced in poetry generation, as the poems must tell a story in only five lines, with constraints on rhyme, stress, and meter. To address these challeng…

GPoeT-2: A GPT-2 Based Poem Generator

2022-05-18 · Kai-Ling Lo, Rami Ariss, Philipp Kurz

This project aims to produce the next volume of machine-generated poetry, a complex art form that can be structured and unstructured, and carries depth in the meaning between the lines. GPoeT-2 is based on fine-tuning a …

DiversityLanguage ModelingLanguage Modelling

Sonnet or Not, Bot? Poetry Evaluation for Large Models and Datasets

2024-06-27 · Melanie Walsh, Anna Preus, Maria Antoniak

Large language models (LLMs) can now generate and recognize poetry. But what do LLMs really know about poetry? We develop a task to evaluate how well LLMs recognize one aspect of English-language poetry--poetic form--whi…

FormMemorization

Sonnet Generation by Training on Non-poetic Texts with Discourse-level Coherence and Poetic Features

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Poetry generation, and creative language generation in general, usually suffers from the lack of large training data. In this paper, we present a novel framework to generate sonnets that does not require training on poem…

Sonnet GenerationText Generation