Optimizing Neural Network Hyperparameters with Gaussian Processes for Dialog Act Classification

TL;DR

This paper demonstrates that using Gaussian process-based Bayesian optimization to tune neural network hyperparameters significantly improves dialog act classification performance and reduces tuning time compared to traditional search methods.

Contribution

The study applies Gaussian process-based Bayesian optimization to hyperparameter tuning in neural networks for dialog act classification, achieving better results faster.

Findings

Hyperparameter optimization with GPs improves model accuracy.

GP-based tuning reduces computational time by a factor of 4.

Enhanced performance over manual and random search methods.

Abstract

Systems based on artificial neural networks (ANNs) have achieved state-of-the-art results in many natural language processing tasks. Although ANNs do not require manually engineered features, ANNs have many hyperparameters to be optimized. The choice of hyperparameters significantly impacts models' performances. However, the ANN hyperparameters are typically chosen by manual, grid, or random search, which either requires expert experiences or is computationally expensive. Recent approaches based on Bayesian optimization using Gaussian processes (GPs) is a more systematic way to automatically pinpoint optimal or near-optimal machine learning hyperparameters. Using a previously published ANN model yielding state-of-the-art results for dialog act classification, we demonstrate that optimizing hyperparameters using GP further improves the results, and reduces the computational time by a factor of 4 compared to a random search. Therefore it is a useful technique for tuning ANN models to yield the best performances for natural language processing tasks.