Published on Mon Oct 14 2019

Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models

Peter Izsak, Shira Guskin, Moshe Wasserblat

Training models on low-resource named entity recognition tasks has been shown to be a challenge. Pre-trained language models trained to extract contextual features from text were shown to improve many natural language processing (NLP) tasks. Such models impose a heavy memory and computational burden.

0
0
0
Abstract

Training models on low-resource named entity recognition tasks has been shown to be a challenge, especially in industrial applications where deploying updated models is a continuous effort and crucial for business operations. In such cases there is often an abundance of unlabeled data, while labeled data is scarce or unavailable. Pre-trained language models trained to extract contextual features from text were shown to improve many natural language processing (NLP) tasks, including scarcely labeled tasks, by leveraging transfer learning. However, such models impose a heavy memory and computational burden, making it a challenge to train and deploy such models for inference use. In this work-in-progress we combined the effectiveness of transfer learning provided by pre-trained masked language models with a semi-supervised approach to train a fast and compact model using labeled and unlabeled examples. Preliminary evaluations show that the compact models can achieve competitive accuracy with 36x compression rate when compared with a state-of-the-art pre-trained language model, and run significantly faster in inference, allowing deployment of such models in production environments or on edge devices.

Fri Aug 23 2019
NLP
A Little Annotation does a Lot of Good: A Study in Bootstrapping Low-resource Named Entity Recognizers
A new way to train machine-learning models in low-resourced languages. It involves using a cross-lingual transfer model, then performing targeted annotation of only uncertain entity.
0
0
0
Sat Dec 22 2018
NLP
A Survey on Deep Learning for Named Entity Recognition
Named entity recognition (NER) is the task to identify mentions of rigid designators from text belonging to predefined semantic types. NER always serves as the foundation for many natural language applications such as question answering, text summarization, and machine translation.
0
0
0
Wed Apr 01 2020
NLP
Deep Entity Matching with Pre-Trained Language Models
0
0
0
Mon Jan 25 2021
NLP
Recent Trends in Named Entity Recognition (NER)
0
0
0
Tue Dec 29 2020
Machine Learning
Few-Shot Named Entity Recognition: A Comprehensive Study
This paper presents a comprehensive study to efficiently build named entity recognition systems. Based upon recent Transformer-based self-supervised pre-trained language models (PLMs) We investigate three orthogonal schemes to improve the model generalization ability for few-shot settings.
1
1
1
Sun Jan 06 2019
Artificial Intelligence
Named Entity Recognition in Electronic Health Records Using Transfer Learning Bootstrapped Neural Networks
Neural networks (NNs) have become the state of the art in many machine learning applications, especially in image and sound processing. However, the success of NNs remains dependent on the availability of large labelled datasets, which is a significant hurdle in many important applications. In our study, we
0
0
0