Transformer-Based Named Entity Recognition for French Using Adversarial Adaptation to Similar Domain Corpora

TL;DR

This paper presents a transformer-based French NER method that employs adversarial adaptation to enhance generalization across similar domain corpora, addressing resource limitations in French language processing.

Contribution

It introduces an adversarial adaptation framework for transformer-based NER in French, improving performance across different datasets and domains.

Findings

Outperforms non-adaptive models on multiple datasets

Enhances feature extraction and generalization in French NER

Effective across various transformer models and domain combinations

Abstract

Named Entity Recognition (NER) involves the identification and classification of named entities in unstructured text into predefined classes. NER in languages with limited resources, like French, is still an open problem due to the lack of large, robust, labelled datasets. In this paper, we propose a transformer-based NER approach for French using adversarial adaptation to similar domain or general corpora for improved feature extraction and better generalization. We evaluate our approach on three labelled datasets and show that our adaptation framework outperforms the corresponding non-adaptive models for various combinations of transformer models, source datasets and target corpora.