Skip to content

anihm136/bilstm-cnn-crf

 
 

Repository files navigation

BiLSTM-CNN-CRF Implementation for Sequence Tagging

This repository contains a slightly modified version of https://github.com/UKPLab/emnlp2017-bilstm-cnn-crf/, used for ASR punctuation in saarthak-agarwal/Video-Summarization. Refer to the original repository for more information on setup and usage.

Citation

If you find the implementation useful, please cite the following paper by the original authors: Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging

@InProceedings{Reimers:2017:EMNLP,
  author    = {Reimers, Nils, and Gurevych, Iryna},
  title     = {{Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging}},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  month     = {09},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  pages     = {338--348},
  url       = {http://aclweb.org/anthology/D17-1035}
}

About

BiLSTM-CNN-CRF architecture for sequence tagging

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages

  • Python 100.0%