Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting
This work addresses the need for better ensemble methods in NLP, offering a domain-specific improvement over existing approaches.
The paper tackles the problem of suboptimal ensemble performance in NLP by moving beyond simple averaging to weight models based on individual performance and similarity using Topological Data Analysis, resulting in improved text classification accuracy and uncertainty estimation.
In machine learning, ensembles are important tools for improving the model performance. In natural language processing specifically, ensembles boost the performance of a method due to multiple large models available in open source. However, existing approaches mostly rely on simple averaging of predictions by ensembles with equal weights for each model, ignoring differences in the quality and conformity of models. We propose to estimate weights for ensembles of NLP models using not only knowledge of their individual performance but also their similarity to each other. By adopting distance measures based on Topological Data Analysis (TDA), we improve our ensemble. The quality improves for both text classification accuracy and relevant uncertainty estimation.