Modern French Poetry Generation with RoBERTa and GPT-2 - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Modern French Poetry Generation with RoBERTa and GPT-2

Résumé

We present a novel neural model for modern poetry generation in French. The model consists of two pretrained neural models that are fine-tuned for the poem generation task. The encoder of the model is a RoBERTa based one while the decoder is based on GPT-2. This way the model can benefit from the superior natural language understanding performance of RoBERTa and the good natural language generation performance of GPT-2. Our evaluation shows that the model can create French poetry successfully. On a 5 point scale, the lowest score of 3.57 was given by human judges to typicality and emotionality of the output poetry while the best score of 3.79 was given to understandability.
Fichier principal
Vignette du fichier
ICCC-2022_10S_Hämäläinen-et-al..pdf (85.11 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03746349 , version 1 (05-08-2022)

Identifiants

  • HAL Id : hal-03746349 , version 1

Citer

Mika Hämäläinen, Khalid Alnajjar, Thierry Poibeau. Modern French Poetry Generation with RoBERTa and GPT-2. 13th International Conference on Computational Creativity (ICCC) 2022, ICCC, Jun 2022, Bolzano, Italy. ⟨hal-03746349⟩
126 Consultations
187 Téléchargements

Partager

Gmail Facebook X LinkedIn More