NeuronBlocks: Building Your NLP DNN Models Like Playing Lego
This toolkit improves productivity for NLP engineers by reducing learning costs and guiding optimal solutions, though it is incremental as it builds on existing DNN frameworks.
The authors tackled the challenge of high overhead for engineers in building NLP DNN models by introducing NeuronBlocks, a toolkit that uses JSON configuration to construct models, and demonstrated its effectiveness on datasets like GLUE, WikiQA, and CoNLL-2003.
Deep Neural Networks (DNN) have been widely employed in industry to address various Natural Language Processing (NLP) tasks. However, many engineers find it a big overhead when they have to choose from multiple frameworks, compare different types of models, and understand various optimization mechanisms. An NLP toolkit for DNN models with both generality and flexibility can greatly improve the productivity of engineers by saving their learning cost and guiding them to find optimal solutions to their tasks. In this paper, we introduce NeuronBlocks\footnote{Code: \url{https://github.com/Microsoft/NeuronBlocks}} \footnote{Demo: \url{https://youtu.be/x6cOpVSZcdo}}, a toolkit encapsulating a suite of neural network modules as building blocks to construct various DNN models with complex architecture. This toolkit empowers engineers to build, train, and test various NLP models through simple configuration of JSON files. The experiments on several NLP datasets such as GLUE, WikiQA and CoNLL-2003 demonstrate the effectiveness of NeuronBlocks.