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

TitleAre Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense
Publication TypeArticle dans des actes
Année de la conférence2021
AuthorsLi, Bingzhi, and Guillaume Wisniewski
Nom de la conférenceProceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Pagination3080–3089
PublisherAssociation for Computational Linguistics
Conference LocationOnline
Abstract

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.

URLhttps://aclanthology.org/2021.eacl-main.269
DOI10.18653/v1/2021.eacl-main.269