End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

Code

• github.com/SuphanutN/Thai-NER-BiLSTM-WordCharEmbedding
  none★ 0
• github.com/akurniawan/pytorch-sequence-tagger
  pytorch★ 0
• github.com/aonotas/deep-crf
  none★ 0
• github.com/sarthakTUM/progressive-neural-networks-for-nlp
  pytorch★ 0
• github.com/soujanyaporia/aspect-extraction
  tf★ 0
• github.com/IBM/MAX-Named-Entity-Tagger
  tf★ 0
• github.com/SNUDerek/multiLSTM
  tf★ 0
• github.com/bestend/tf2-bi-lstm-crf-nni
  tf★ 0
• github.com/SenticNet/aspect-extraction
  tf★ 0
• github.com/guillaumegenthial/tf_ner
  tf★ 0

Abstract

State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF. Our system is truly end-to-end, requiring no feature engineering or data pre-processing, thus making it applicable to a wide range of sequence labeling tasks. We evaluate our system on two data sets for two sequence labeling tasks --- Penn Treebank WSJ corpus for part-of-speech (POS) tagging and CoNLL 2003 corpus for named entity recognition (NER). We obtain state-of-the-art performance on both the two data --- 97.55\% accuracy for POS tagging and 91.21\% F1 for NER.

Tasks

Benchmark Results

Reproductions