Automatic Generation of Factual News Headlines in Finnish - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Automatic Generation of Factual News Headlines in Finnish

Résumé

We present a novel approach to generating news headlines in Finnish for a given news story. We model this as a summarization task where a model is given a news article, and its task is to produce a concise headline describing the main topic of the article. Because there are no openly available GPT-2 models for Finnish, we will first build such a model using several corpora. The model is then fine-tuned for the headline generation task using a massive news corpus. The system is evaluated by 3 expert journalists working in a Finnish media house. The results showcase the usability of the presented approach as a headline suggestion tool to facilitate the news production process.
Fichier principal
Vignette du fichier
INLG_2022___Finnish_Headline_Generation (2).pdf (211.26 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03731353 , version 1 (21-07-2022)

Identifiants

  • HAL Id : hal-03731353 , version 1

Citer

Maximilian Koppatz, Khalid Alnajjar, Mika Hämäläinen, Thierry Poibeau. Automatic Generation of Factual News Headlines in Finnish. 15th International Natural Language Generation Conference (INLG), Jul 2022, Seattle, United States. ⟨hal-03731353⟩
40 Consultations
44 Téléchargements

Partager

Gmail Facebook X LinkedIn More