The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning

05/31/2019
by   Bonggun Shin, et al.
0

Recent advances in deep learning have facilitated the demand of neural models for real applications. In practice, these applications often need to be deployed with limited resources while keeping high accuracy. This paper touches the core of neural models in NLP, word embeddings, and presents a new embedding distillation framework that remarkably reduces the dimension of word embeddings without compromising accuracy. A novel distillation ensemble approach is also proposed that trains a high-efficient student model using multiple teacher models. In our approach, the teacher models play roles only during training such that the student model operates on its own without getting supports from the teacher models during decoding, which makes it eighty times faster and lighter than other typical ensemble methods. All models are evaluated on seven document classification datasets and show a significant advantage over the teacher models for most cases. Our analysis depicts insightful transformation of word embeddings from distillation and suggests a future direction to ensemble approaches using neural models.

READ FULL TEXT

page 2

page 3

09/25/2019

Extreme Language Model Compression with Optimal Subwords and Shared Projections

Pre-trained deep neural network language models such as ELMo, GPT, BERT ...
11/07/2017

Moonshine: Distilling with Cheap Convolutions

Model distillation compresses a trained machine learning model, such as ...
02/26/2021

A Meta-embedding-based Ensemble Approach for ICD Coding Prediction

International Classification of Diseases (ICD) are the de facto codes us...
11/08/2020

Ensembled CTR Prediction via Knowledge Distillation

Recently, deep learning-based models have been widely studied for click-...
09/13/2020

DistilE: Distiling Knowledge Graph Embeddings for Faster and Cheaper Reasoning

Knowledge Graph Embedding (KGE) is a popular method for KG reasoning and...
09/08/2019

Transformer to CNN: Label-scarce distillation for efficient text classification

Significant advances have been made in Natural Language Processing (NLP)...
02/24/2017

Use Generalized Representations, But Do Not Forget Surface Features

Only a year ago, all state-of-the-art coreference resolvers were using a...