Developing an open-source, rule-based proofreading tool

Authors:
Marcin Miłkowski
Affiliations:
Institute of Philosophy and Sociology, Polish Academy of Sciences, Nowy Świat 72, Warsaw 00-330, Poland
Venue:
Software—Practice & Experience
Year:
2010

Citing 5
Cited 4

Automatic Rule Acquisition for Spelling Correction

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
A corpus-based bootstrapping algorithm for Semi-Automated semantic lexicon construction

Natural Language Engineering
Arabic GramCheck: a grammar checker for Arabic: Research Articles

Software—Practice & Experience
Hunmorph: open source word analysis

Software '05 Proceedings of the Workshop on Software
Finite state tools for natural language processing

Proceedings of the COLING-2000 Workshop on Using Toolsets and Architectures To Build NLP Systems

Using SRX standard for sentence segmentation

LTC'09 Proceedings of the 4th conference on Human language technology: challenges for computer science and linguistics
Combining polish morphosyntactic taggers

SIIS'11 Proceedings of the 2011 international conference on Security and Intelligent Information Systems
Handling outlandish occurrences: using rules and lexicons for correcting NLP articles

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
Detecting API documentation errors

Proceedings of the 2013 ACM SIGPLAN international conference on Object oriented programming systems languages & applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we show how an open-source, language-independent proofreading tool has been built. Many languages lack contextual proofreading tools; for many others, only partial solutions are available. Using existing, largely language-independent tools and collaborative processes it is possible to develop a practical style and grammar checker and to fight the digital divide in countries where commercial linguistic application software is unavailable or too expensive for average users. The described solution depends on relatively easily available language resources and does not require a fully formalized grammar nor a deep parser, yet it can detect many frequent context-dependent spelling mistakes, as well as grammatical, punctuation, usage, and stylistic errors. Copyright © 2010 John Wiley & Sons, Ltd.