Automatic Poetic Metre Detection for Czech Verse

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68378068%3A_____%2F24%3A00598455" target="_blank" >RIV/68378068:_____/24:00598455 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21240/24:00376478

Výsledek na webu

<a href="https://ojs.utlib.ee/index.php/smp/article/view/24421" target="_blank" >https://ojs.utlib.ee/index.php/smp/article/view/24421</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.12697/smp.2024.11.1.02" target="_blank" >10.12697/smp.2024.11.1.02</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Poetic Metre Detection for Czech Verse

Popis výsledku v původním jazyce

Metrical analysis of verse is an essential and challenging task in the research on versification consisting of analysing a poem and deciding which metre it is written in. Thanks to existing corpora, we can take advantage of data-driven approaches, which can be better suited to the specific versification problems at hand than rulebased systems. This work analyses the Czech accentual-syllabic verse and automatic metre assignment using the vast and annotated Corpus of Czech Verse. We define the problem as a sequence tagging task and approach it using a machine learning model and many different input data configurations. In comparison to this approach, we reimplement the existing data-driven system KVĚTA. Our results demonstrate that the bidirectional LSTM-CRF sequence tagging model, enhanced with syllable embeddings, significantly outperforms the existing KVĚTA system, with predictions achieving 99.61% syllable accuracy, 98.86% line accuracy, and 90.40% poem accuracy. The model also achieved competitive results with token embeddings. One of the most interesting findings is that the best results are obtained by inputting sequences representing whole poems instead of individual poem lines.

Název v anglickém jazyce

Automatic Poetic Metre Detection for Czech Verse

Popis výsledku anglicky

Metrical analysis of verse is an essential and challenging task in the research on versification consisting of analysing a poem and deciding which metre it is written in. Thanks to existing corpora, we can take advantage of data-driven approaches, which can be better suited to the specific versification problems at hand than rulebased systems. This work analyses the Czech accentual-syllabic verse and automatic metre assignment using the vast and annotated Corpus of Czech Verse. We define the problem as a sequence tagging task and approach it using a machine learning model and many different input data configurations. In comparison to this approach, we reimplement the existing data-driven system KVĚTA. Our results demonstrate that the bidirectional LSTM-CRF sequence tagging model, enhanced with syllable embeddings, significantly outperforms the existing KVĚTA system, with predictions achieving 99.61% syllable accuracy, 98.86% line accuracy, and 90.40% poem accuracy. The model also achieved competitive results with token embeddings. One of the most interesting findings is that the best results are obtained by inputting sequences representing whole poems instead of individual poem lines.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

60205 - Literary theory

Projekt

<a href="/cs/project/TL05000288" target="_blank" >TL05000288: Analýza motivických klastrů z oblasti aktuálních kulturně-společenských témat a jejich aplikace na materiál uměleckých textů 19. a počátku 20. století</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Studia Metrica et Poetica

ISSN

2346-6901

e-ISSN

2346-691X

Svazek periodika

11

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

EE - Estonská republika

Počet stran výsledku

18

Strana od-do

44-61

Kód UT WoS článku

001312919300002

EID výsledku v databázi Scopus

2-s2.0-85203253700