Abdibayev, Almas ; Igarashi, Yohei ; Riddell, Allen ; Rockmore, Daniel (2023)
Limericks and Computational Poetics: The Minimal Pairs Framework. Computational Challenges for Poetic Analysis and Synthesis.
In: Journal of Computational Literary Studies, 2022, 1 (1)
doi: 10.26083/tuprints-00023258
Artikel, Zweitveröffentlichung, Verlagsversion
Kurzbeschreibung (Abstract)
Computational poetics encompasses the wide range of challenges implicit in analyzing and generating poetry – in all of its many forms – through computational techniques and frameworks. In this paper, we build on a nascent body of work that has proposed the use of the limerick as a ‘model organism’ for computational poetics, and in particular the use of Benchmarked Poetic Minimal Pairs (BPoMP) as an investigative framework, especially for the evaluation of the poetic abilities of deep learning language models. To that end, we include results for two new BPoMP tasks of interest for limerick analysis – the word deletion task and the limerick completion tasks. We include a release of a data set for the deletion task. We also offer up a suite of an additional ten BPoMP challenges whose precise formulations still require detail.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Abdibayev, Almas ; Igarashi, Yohei ; Riddell, Allen ; Rockmore, Daniel |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Limericks and Computational Poetics: The Minimal Pairs Framework. Computational Challenges for Poetic Analysis and Synthesis |
| Sprache: | Englisch |
| Publikationsjahr: | 2023 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 2022 |
| Verlag: | Universitäts- und Landesbibliothek Darmstadt |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Journal of Computational Literary Studies |
| Jahrgang/Volume einer Zeitschrift: | 1 |
| (Heft-)Nummer: | 1 |
| Kollation: | 26 Seiten |
| DOI: | 10.26083/tuprints-00023258 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/23258 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichung von TUjournals |
| Kurzbeschreibung (Abstract): | Computational poetics encompasses the wide range of challenges implicit in analyzing and generating poetry – in all of its many forms – through computational techniques and frameworks. In this paper, we build on a nascent body of work that has proposed the use of the limerick as a ‘model organism’ for computational poetics, and in particular the use of Benchmarked Poetic Minimal Pairs (BPoMP) as an investigative framework, especially for the evaluation of the poetic abilities of deep learning language models. To that end, we include results for two new BPoMP tasks of interest for limerick analysis – the word deletion task and the limerick completion tasks. We include a release of a data set for the deletion task. We also offer up a suite of an additional ten BPoMP challenges whose precise formulations still require detail. |
| Freie Schlagworte: | limericks, computational poetics, minimal pairs, evaluation, language models |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-232589 |
| Zusätzliche Informationen: | Urspr. Konferenzveröffentlichung/Originally conference publication: 1st Annual Conference of Computational Literary Studies, 01.-02.06.2022, Darmstadt, Germany |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 800 Literatur > 800 Literatur, Rhetorik, Literaturwissenschaft |
| Fachbereich(e)/-gebiet(e): | 02 Fachbereich Gesellschafts- und Geschichtswissenschaften > Institut für Sprach- und Literaturwissenschaft > Digital Philology - Neuere deutsche Literaturwissenschaft 02 Fachbereich Gesellschafts- und Geschichtswissenschaften 02 Fachbereich Gesellschafts- und Geschichtswissenschaften > Institut für Sprach- und Literaturwissenschaft |
| Hinterlegungsdatum: | 21 Feb 2023 10:25 |
| Letzte Änderung: | 27 Feb 2023 12:48 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum