Papers › FLERT: Document-Level Features for Named Entity Recognition

FLERT: Document-Level Features for Named Entity Recognition

13 Nov 2020arXiv:2011.06993archive 2025-07-28

Stefan Schweter, Alan Akbik

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

flairNLP/flair officialmentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

NERNamed Entity RecognitionNamed Entity Recognition (NER)Sentencenamed-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Named Entity Recognition (NER) CoNLL 2002 (Dutch) FLERT XLM-R F1 95.21 #2 of 6 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2002 (Spanish) FLERT XLM-R F1 90.14 #4 of 6 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) FLERT XLM-R F1 94.09 #6 of 73 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (German) FLERT XLM-R F1 88.34 #2 of 6 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (German) Revised FLERT XLM-R F1 92.23 #1 of 5 Archive leaderboard report
Named Entity Recognition (NER) FindVehicle FLERT F1 Score 80.9 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections