Capitalization and Punctuation Restoration: a Survey

TL;DR

This survey reviews historical and modern techniques for restoring punctuation and casing in text, crucial for NLP tasks involving unpunctuated or un-cased sources like speech recognition outputs and social media texts.

Contribution

It provides a comprehensive overview of methods, challenges, and future research directions in punctuation and casing restoration for unstructured text.

Findings

Historical and recent techniques are compared and analyzed.

Current challenges in punctuation and casing restoration are identified.

Future research directions are proposed.

Abstract

Ensuring proper punctuation and letter casing is a key pre-processing step towards applying complex natural language processing algorithms. This is especially significant for textual sources where punctuation and casing are missing, such as the raw output of automatic speech recognition systems. Additionally, short text messages and micro-blogging platforms offer unreliable and often wrong punctuation and casing. This survey offers an overview of both historical and state-of-the-art techniques for restoring punctuation and correcting word casing. Furthermore, current challenges and research directions are highlighted.