Improving Document Clustering by Eliminating Unnatural Language

TL;DR

This paper introduces a method to detect and remove unnatural language elements from technical documents, significantly improving document clustering performance by up to 15%.

Contribution

It presents a novel annotated corpus and a classification model for identifying unnatural language components across various document formats.

Findings

Removing unnatural language improves clustering accuracy by up to 15%

Developed a multiclass classifier for unnatural language detection

Created a publicly available annotated corpus and detection tool

Abstract

Technical documents contain a fair amount of unnatural language, such as tables, formulas, pseudo-codes, etc. Unnatural language can be an important factor of confusing existing NLP tools. This paper presents an effective method of distinguishing unnatural language from natural language, and evaluates the impact of unnatural language detection on NLP tasks such as document clustering. We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories. First, we create a new annotated corpus by collecting slides and papers in various formats, PPT, PDF, and HTML, where unnatural language components are annotated into four categories. We then explore features available from plain text to build a statistical model that can handle any format as long as it is converted into plain text. Our experiments show that removing unnatural language components gives an absolute improvement in document clustering up to 15%. Our corpus and tool are publicly available.