Papers › Robust Lexical Features for Improved Neural Network Named-Entity Recognition

Robust Lexical Features for Improved Neural Network Named-Entity Recognition

9 Jun 2018COLING 2018 8arXiv:1806.03489archive 2025-07-28

Abbas Ghaddar, Philippe Langlais

Neural network approaches to Named-Entity Recognition reduce the need for carefully hand-crafted features. While some features do remain in state-of-the-art systems, lexical features have been mostly discarded, with the exception of gazetteers. In this work, we show that this is unfair: lexical features are actually quite useful. We propose to embed words and entity types into a low-dimensional vector space we train from annotated data produced by distant supervision thanks to Wikipedia. From this, we compute - offline - a feature vector representing each word. When used with a vanilla recurrent neural network model, this representation yields substantial improvements. We establish a new state-of-the-art F1 score of 87.95 on ONTONOTES 5.0, while matching state-of-the-art performance with a F1 score of 91.73 on the over-studied CONLL-2003 dataset.

PaperPDFConference PDFCode

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

Code

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

Named Entity RecognitionNamed Entity Recognition (NER)named-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Named Entity Recognition (NER) CoNLL 2003 (English) Bi-LSTM-CRF + Lexical Features F1 91.73 #55 of 73 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) Bi-LSTM-CRF + Lexical Features F1 87.95 #23 of 28 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.

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