Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models
This work addresses the problem of deploying efficient models in industrial or edge settings where labeled data is scarce, though it is incremental as it builds on existing methods.
The paper tackles the challenge of training compact models for low-resource named entity recognition by combining transfer learning from pre-trained language models with a semi-supervised approach, achieving competitive accuracy with a 36x compression rate and significantly faster inference.
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.