Back-Translation for Named Entity Recognition

Data Processing

Method:

  • As each word can appear in two vocabularies, we can have multiple labels for each word
  • The labelling is done independently of the context
  • For each word in the MISC vocabulary from CONLL, we look in wikidata what the instance it belongs to is, by looking at the parent node through the relationship ‘is an instance of’.
  • Given this list of classes, we look at all their instances in wikidata to create the MISC vocabulary for this dataset

Benchmarks

Modeling Approaches

KALM Architecture

Multi-Label Classification with BERT

Translation Approach

Discussion

References:

Acknowledgements

--

--

--

Paxton Maeder-York was previously a product manager at Auris Health. He has a B.S. in BME, an M.S. in CSE, and an M.B.A. from Harvard University.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Best Activation Function for Training Neural Networks

CatBoost Quickstart — ML Classification

Random Convolutional Kernel Transform — Understanding Paper

Regression with Infinitely Many Parameters: Gaussian Processes

Real time head to head racing using vehicle tracking

How to stop fraud with ML — best practices at Bolt

Developing Industrial Machine Learning Projects: 3 Common Mistakes to Avoid

Fine Tuning BERT: Multilabel Text Classification

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Paxton Maeder-York

Paxton Maeder-York

Paxton Maeder-York was previously a product manager at Auris Health. He has a B.S. in BME, an M.S. in CSE, and an M.B.A. from Harvard University.

More from Medium

Sentiment Analysis Without Modeling: TextBlob vs. VADER vs. Flair

Python for Data Science and Machine Learning: An Introduction

Neural Machine Translation

Custom Transformers in Scikit-learn Pipeline