Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings
Sinha, Soumen, Rahnamayan, Shahryar, Bidgoli, Azam Asilian
–arXiv.org Artificial Intelligence
Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations (barcodes) instead of real-valued features can be used for NLP embeddings derived from machine learning models such as BERT. Thresholding is a common method for converting continuous embeddings into binary representations, often using a fixed threshold across all features. We propose a Coordinate Search-based optimization framework that instead identifies the optimal threshold for each feature, demonstrating that feature-specific thresholds lead to improved performance in binary encoding. This ensures that the binary representations are both accurate and efficient, enhancing performance across various features. Our optimal barcode representations have shown promising results in various NLP applications, demonstrating their potential to transform text representation. We conducted extensive experiments and statistical tests on different NLP tasks and datasets to evaluate our approach and compare it to other thresholding methods. Binary embeddings generated using using optimal thresholds found by our method outperform traditional binarization methods in accuracy. This technique for generating binary representations is versatile and can be applied to any features, not just limited to NLP embeddings, making it useful for a wide range of domains in machine learning applications.
arXiv.org Artificial Intelligence
Jul-24-2025
- Country:
- Asia (0.04)
- Europe
- Netherlands > South Holland
- Delft (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Netherlands > South Holland
- North America
- Canada
- Ontario
- Niagara Region > St. Catharines (0.04)
- Waterloo Region > Waterloo (0.04)
- Quebec > Capitale-Nationale Region
- Quebec City (0.04)
- Québec (0.04)
- Ontario
- United States > New York
- New York County > New York City (0.04)
- Canada
- Genre:
- Research Report
- Experimental Study (0.48)
- New Finding (0.68)
- Research Report
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Evolutionary Systems (0.68)
- Neural Networks > Deep Learning (0.67)
- Statistical Learning (0.93)
- Natural Language (1.00)
- Representation & Reasoning
- Optimization (0.88)
- Search (0.89)
- Machine Learning
- Information Technology > Artificial Intelligence