DeepZensols: Deep Natural Language Processing Framework

TL;DR

DeepZensols is a framework designed to facilitate the reproducibility of NLP deep learning experiments, enabling consistent results and simplifying model creation, training, and evaluation.

Contribution

It introduces a framework that ensures reproducibility and ease of use for NLP deep learning models, addressing reproducibility challenges in ML research.

Findings

Provides consistent results across experiments

Simplifies creation and evaluation of NLP models

Enhances reproducibility in NLP research

Abstract

Reproducing results in publications by distributing publicly available source code is becoming ever more popular. Given the difficulty of reproducing machine learning (ML) experiments, there have been significant efforts in reducing the variance of these results. As in any science, the ability to consistently reproduce results effectively strengthens the underlying hypothesis of the work, and thus, should be regarded as important as the novel aspect of the research itself. The contribution of this work is a framework that is able to reproduce consistent results and provides a means of easily creating, training, and evaluating natural language processing (NLP) deep learning (DL) models.