A Conceptual Framework For Trie-Augmented Neural Networks (TANNS)

TL;DR

This paper introduces Trie-Augmented Neural Networks (TANNs), a hierarchical model combining trie structures with neural networks to improve interpretability and maintain competitive performance in text classification tasks.

Contribution

The paper presents a novel TANN architecture that enhances decision transparency in neural networks for text classification, demonstrating comparable or improved results over traditional models.

Findings

TANNs achieve similar or slightly better accuracy than traditional RNNs and FNNs.

TANNs improve interpretability through structured decision-making.

Implementation challenges and limitations are discussed.

Abstract

Trie-Augmented Neural Networks (TANNs) combine trie structures with neural networks, forming a hierarchical design that enhances decision-making transparency and efficiency in machine learning. This paper investigates the use of TANNs for text and document classification, applying Recurrent Neural Networks (RNNs) and Feed forward Neural Networks (FNNs). We evaluated TANNs on the 20 NewsGroup and SMS Spam Collection datasets, comparing their performance with traditional RNN and FFN Networks with and without dropout regularization. The results show that TANNs achieve similar or slightly better performance in text classification. The primary advantage of TANNs is their structured decision-making process, which improves interpretability. We discuss implementation challenges and practical limitations. Future work will aim to refine the TANNs architecture for more complex classification tasks.