Transformer-Based Named Entity Recognition for French Using Adversarial Adaptation to Similar Domain Corpora
Preprint
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Named Entity Recognition by Using XLNet-BiLSTM-CRFNeural Processing Letters, 2021
- WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER2021
- Evaluating Pretrained Transformer-based Models on the Task of Fine-Grained Named Entity Recognition2020
- CamemBERT: a Tasty French Language Model2020
- Chinese Named Entity Recognition with BertDEStech Transactions on Computer Science and Engineering, 2019
- Learning multilingual named entity recognition from WikipediaArtificial Intelligence, 2013
- Text Chunking Using Transformation-Based Learning1999