Efficient Multilingual Name Type Classification Using Convolutional Networks

TL;DR

This paper introduces a CNN-based model, Onomas-CNN X, for multilingual name classification that is highly efficient and accurate, outperforming transformer models in speed and energy consumption on CPU hardware.

Contribution

The paper presents a novel CNN architecture for multilingual name classification that achieves high accuracy and efficiency, demonstrating competitiveness with large transformer models.

Findings

Achieves 92.1% accuracy on a large multilingual dataset.

Processes 2,813 names per second on a single CPU core.

Reduces energy consumption by a factor of 46 compared to transformer baselines.

Abstract

We present a convolutional neural network approach for classifying proper names by language and entity type. Our model, Onomas-CNN X, combines parallel convolution branches with depthwise-separable operations and hierarchical classification to process names efficiently on CPU hardware. We evaluate the architecture on a large multilingual dataset covering 104 languages and four entity types (person, organization, location, other). Onomas-CNN X achieves 92.1% accuracy while processing 2,813 names per second on a single CPU core - 46 times faster than fine-tuned XLM-RoBERTa with comparable accuracy. The model reduces energy consumption by a factor of 46 compared to transformer baselines. Our experiments demonstrate that specialized CNN architectures remain competitive with large pre-trained models for focused NLP tasks when sufficient training data exists.