DeepZensols: Deep Natural Language Processing Framework
This work addresses reproducibility issues for researchers in NLP, though it is incremental as it builds on existing efforts to reduce variance in results.
The authors tackled the problem of reproducing machine learning experiments in NLP by introducing DeepZensols, a framework that enables consistent reproduction of results and simplifies the creation, training, and evaluation of deep learning models.
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.