Evaluating Pretrained Transformer-based Models on the Task of Fine-Grained Named Entity Recognition
| Autor: | Lisa Veiber, Tegawendé F. Bissyandé, Kevin Allix, Cedric Lothritz, Jacques Klein |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science [C05] [Engineering
computing & technology] Computer science business.industry 05 social sciences 010501 environmental sciences computer.software_genre Sciences informatiques [C05] [Ingénierie informatique & technologie] 01 natural sciences Field (computer science) fine-grained Named Entity Recognition Task (project management) Named-entity recognition Transformers 0502 economics and business Artificial intelligence 050207 economics F1 score business computer Natural language processing 0105 earth and related environmental sciences Transformer (machine learning model) Natural Language Processing |
| Zdroj: | BASE-Bielefeld Academic Search Engine COLING |
| Popis: | Named Entity Recognition (NER) is a fundamental Natural Language Processing (NLP) task and has remained an active research field. In recent years, transformer models and more specifically the BERT model developed at Google revolutionised the field of NLP. While the performance of transformer-based approaches such as BERT has been studied for NER, there has not yet been a study for the fine-grained Named Entity Recognition (FG-NER) task. In this paper, we compare three transformer-based models (BERT, RoBERTa, and XLNet) to two non-transformer-based models (CRF and BiLSTM-CNN-CRF). Furthermore, we apply each model to a multitude of distinct domains. We find that transformer-based models incrementally outperform the studied non-transformer-based models in most domains with respect to the F1 score. Furthermore, we find that the choice of domains significantly influenced the performance regardless of the respective data size or the model chosen. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|