Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense - HAL Accéder directement au contenu
Communication dans un congrès Année : 2021

Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense

Résumé

We evaluate the ability of Bert embeddings to represent tense information, taking French and Chinese as a case study. In French, the tense information is expressed by verb morphology and can be captured by simple surface information. On the contrary, tense interpretation in Chinese is driven by abstract, lexical, syntactic and even pragmatic information. We show that while French tenses can easily be predicted from sentence representations, results drop sharply for Chinese, which suggests that Bert is more likely to memorize shallow patterns from the training data rather than uncover abstract properties.
Fichier principal
Vignette du fichier
chinese_tense.pdf ( 143.19 Ko ) Télécharger
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

halshs-03197072, version 1 (13-04-2021)

Identifiants

  • HAL Id : halshs-03197072 , version 1

Citer

Bingzhi Li, Guillaume Wisniewski. Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense. EACL 2021, Apr 2021, Kiev (on line), Ukraine. ⟨halshs-03197072⟩
138 Consultations
118 Téléchargements
Dernière date de mise à jour le 23/06/2024
comment ces indicateurs sont-ils produits

Partager

Gmail Facebook Twitter LinkedIn Plus