Tutorial : Reproducible Implementation of End-to-end-Sequence-Labeling-via-Bi-directional-LSTM-CNNs-CRF

Abstract

In this tutorial we will demonstrate how to implement a state of the art Bi-directional LSTM-CNN-CRF architecture (Published at ACL’16. Link To Paper) for Named Entity Recognition using Pytorch. The main aim of the tutorial is to make the audience comfortable with pytorch using this tutorial and give a step-by-step walk through of the Bi-LSTM-CNN-CRF architecture for NER. Some familiarity with pytorch (or any other deep learning framework) would definitely be a plus.

Publication
In Enabling Reproducilibity in Machine Learning MLTRAIN@RML (ICML 2018)
Date