Comparative Analysis of Improved Versions of BERT Models on Chinese NLP Tasks

Résumé fourni par la source

BERT is a pre-trained language representation model that has received a lot of attention for its impressive results in Natural Language Processing (NLP) tasks, such as sentiment analysis and text classification. This inspired many BERT-based models to be created that improved on the original in different ways. Examples of these models include RoBERTa, which improves on BERT’s pretraining; K-BERT, which uses Knowledge Graphs to improve BERT’s domain-specific knowledge; and many others. In this paper, we will test these BERT-based models with various datasets and present a comparative analysis of the models.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.