Chère maison or maison chère? Transformer-based Prediction of Adjective Placement in French - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2023

Chère maison or maison chère? Transformer-based Prediction of Adjective Placement in French

Résumé

In French, the placement of the adjective within a noun phrase is subject to variation: it can appear either before or after the noun. We conduct experiments to assess whether transformerbased language models are able to learn the adjective position in noun phrases in French-a position which depends on several linguistic factors. Prior findings have shown that transformer models are insensitive to permutated word order, but in this work, we show that finetuned models are successful at learning and selecting the correct position of the adjective. However, this success can be attributed to the process of finetuning rather than the linguistic knowledge acquired during pretraining, as evidenced by the low accuracy of experiments of classification that make use of pretrained embeddings. Comparing the finetuned models to the choices of native speakers (with a questionnaire), we notice that the models favor context and global syntactic roles, and are weaker with complex structures and fixed expressions.
Fichier principal
Vignette du fichier
2023.findings-eacl.124.pdf (560.92 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04148637 , version 1 (04-07-2023)

Licence

Identifiants

Citer

Eleni Metheniti, Tim van de Cruys, Wissam Kerkri, Juliette Thuilier, Nabil Hathout. Chère maison or maison chère? Transformer-based Prediction of Adjective Placement in French. EACL 2023, pp.1668-1683, 2023, ⟨10.18653/v1/2023.findings-eacl.124⟩. ⟨hal-04148637⟩
54 Consultations
48 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More