Named Entity Recognition with Bidirectional LSTM-CNNs

Code

• github.com/mdiannna/Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs-adaptation
  tf★ 0
• github.com/shakimov/SimpleQA-NER
  tf★ 0
• github.com/mxhofer/Named-Entity-Recognition-BidirectionalLSTM-CNN-CoNLL
  tf★ 0
• github.com/zalandoresearch/flair
  pytorch★ 0
• github.com/niccolot/NER_biLSTM-CNN
  tf★ 0
• github.com/mshehrozsajjad/Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs
  tf★ 0
• github.com/rikhuijzer/nlu_datasets
  none★ 0
• github.com/kamalkraj/Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs
  tf★ 0
• github.com/ZubinGou/NER-BiLSTM-CRF-PyTorch
  pytorch★ 0
• github.com/vasilikivmo/repo2_Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs_amalkraj
  tf★ 0

Abstract

Named entity recognition is a challenging task that has traditionally required large amounts of knowledge in the form of feature engineering and lexicons to achieve high performance. In this paper, we present a novel neural network architecture that automatically detects word- and character-level features using a hybrid bidirectional LSTM and CNN architecture, eliminating the need for most feature engineering. We also propose a novel method of encoding partial lexicon matches in neural networks and compare it to existing approaches. Extensive evaluation shows that, given only tokenized text and publicly available word embeddings, our system is competitive on the CoNLL-2003 dataset and surpasses the previously reported state of the art performance on the OntoNotes 5.0 dataset by 2.13 F1 points. By using two lexicons constructed from publicly-available sources, we establish new state of the art performance with an F1 score of 91.62 on CoNLL-2003 and 86.28 on OntoNotes, surpassing systems that employ heavy feature engineering, proprietary lexicons, and rich entity linking information.

Tasks

Benchmark Results

Reproductions