About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Stefan Schweter
- sl:arxiv_num : 2011.06993
- sl:arxiv_published : 2020-11-13T16:13:59Z
- sl:arxiv_summary : Current state-of-the-art approaches for named entity recognition (NER) using
BERT-style transformers typically use one of two different approaches: (1) The
first fine-tunes the transformer itself on the NER task and adds only a simple
linear layer for word-level predictions. (2) The second uses the transformer
only to provide features to a standard LSTM-CRF sequence labeling architecture
and thus performs no fine-tuning. In this paper, we perform a comparative
analysis of both approaches in a variety of settings currently considered in
the literature. In particular, we evaluate how well they work when
document-level features are leveraged. Our evaluation on the classic CoNLL
benchmark datasets for 4 languages shows that document-level features
significantly improve NER quality and that fine-tuning generally outperforms
the feature-based approaches. We present recommendations for parameters as well
as several new state-of-the-art numbers. Our approach is integrated into the
Flair framework to facilitate reproduction of our experiments.@en
- sl:arxiv_title : FLERT: Document-Level Features for Named Entity Recognition@en
- sl:arxiv_updated : 2020-11-13T16:13:59Z
- sl:bookmarkOf : https://arxiv.org/abs/2011.06993
- sl:creationDate : 2020-12-01
- sl:creationTime : 2020-12-01T09:25:14Z
Documents with similar tags (experimental)