LAMVI-2: A Visual Tool for Comparing and Tuning Word Embedding Models
This tool addresses the problem of time-consuming model comparison for developers working with deep learning in text applications, though it is incremental as it builds on existing visualization approaches.
The paper tackles the complexity of tuning deep learning models by introducing LAMVI-2, a visual analytics tool that helps developers compare hyperparameter settings and outcomes for word-embedding models, enabling quicker and more accurate model selection.
Tuning machine learning models, particularly deep learning architectures, is a complex process. Automated hyperparameter tuning algorithms often depend on specific optimization metrics. However, in many situations, a developer trades one metric against another: accuracy versus overfitting, precision versus recall, smaller models and accuracy, etc. With deep learning, not only are the model's representations opaque, the model's behavior when parameters "knobs" are changed may also be unpredictable. Thus, picking the "best" model often requires time-consuming model comparison. In this work, we introduce LAMVI-2, a visual analytics system to support a developer in comparing hyperparameter settings and outcomes. By focusing on word-embedding models ("deep learning for text") we integrate views to compare both high-level statistics as well as internal model behaviors (e.g., comparing word 'distances'). We demonstrate how developers can work with LAMVI-2 to more quickly and accurately narrow down an appropriate and effective application-specific model.