FLERT: Document-Level Features for Named Entity Recognition
This work addresses the limitation of sentence-level NER for researchers and practitioners, though it is incremental as it builds on existing transformer-based models.
The paper tackled the problem of named entity recognition (NER) by evaluating document-level features to capture cross-sentence information, achieving new state-of-the-art scores on several CoNLL-03 benchmark datasets.
Current state-of-the-art approaches for named entity recognition (NER) typically consider text at the sentence-level and thus do not model information that crosses sentence boundaries. However, the use of transformer-based models for NER offers natural options for capturing document-level features. In this paper, we perform a comparative evaluation of document-level features in the two standard NER architectures commonly considered in the literature, namely "fine-tuning" and "feature-based LSTM-CRF". We evaluate different hyperparameters for document-level features such as context window size and enforcing document-locality. We present experiments from which we derive recommendations for how to model document context and present new state-of-the-art scores on several CoNLL-03 benchmark datasets. Our approach is integrated into the Flair framework to facilitate reproduction of our experiments.