Word-level Human Interpretable Scoring Mechanism for Novel Text Detection Using Tsetlin Machines

TL;DR

This paper introduces a Tsetlin machine-based method for word-level novelty detection that provides interpretable scores for individual words, enabling fine-grained analysis of what makes documents novel.

Contribution

It presents a novel Tsetlin machine architecture that scores words based on their contribution to novelty, offering interpretability at the word level unlike traditional deep neural networks.

Findings

Successfully measures word contribution to novelty

Breaks down novelty into interpretable phrases

Demonstrates effective word-level novelty detection

Abstract

Recent research in novelty detection focuses mainly on document-level classification, employing deep neural networks (DNN). However, the black-box nature of DNNs makes it difficult to extract an exact explanation of why a document is considered novel. In addition, dealing with novelty at the word-level is crucial to provide a more fine-grained analysis than what is available at the document level. In this work, we propose a Tsetlin machine (TM)-based architecture for scoring individual words according to their contribution to novelty. Our approach encodes a description of the novel documents using the linguistic patterns captured by TM clauses. We then adopt this description to measure how much a word contributes to making documents novel. Our experimental results demonstrate how our approach breaks down novelty into interpretable phrases, successfully measuring novelty.