Projects:2015s1-31 Cracking the Voynich manuscript code

Team

Supervisors

• Prof. Derek Abbott
• Dr. Brian Ng
• Maryam Ebrahimpour

Honours Students

• Andrew McInnes
• Lifei Wang

Project Information

Background

The Voynich Manuscript is a document written in an unknown script that has been carbon dated back to the early 15th century [1] and believed to be created within Europe [2]. Named after Wilfrid Voynich, whom purchased the folio in 1912, the manuscript has become a well-known mystery within linguistics and cryptology. It is divided into several different section based on the nature of the drawings [3]. These sections are:

• Herbal
• Astronomical
• Biological
• Cosmological
• Pharmaceutical
• Recipes

The folio numbers and examples of each section are outlined in appendix section A.2. In general, the Voynich Manuscript has fallen into three particular hypotheses [4]. These are as follows:

• Cipher Text: The text is encrypted.
• Plain Text: The text is in a plain, natural language that is currently unidentified.
• Hoax: The text has no meaningful information.

Note that the manuscript may fall into more than one of these hypotheses [4]. It may be that the manuscript is written through steganography, the concealing of the true meaning within the possibly meaningless text.

Technical Background

The vast majority of the project relies on a technique known as data mining. Data mining is the process of taking and analysing a large data set in order to uncover particular patterns and correlations within said data thus creating useful knowledge [6]. In terms of the project, data shall be acquired from the Interlinear Archive, a digital archive of transcriptions from the Voynich Manuscript, and other sources of digital texts in known languages. Data mined from the Interlinear Archive will be tested and analysed for specific linguistic properties using varying statistical methods.

The Interlinear Archive, as mentioned, will be the main source of data in regards to the Voynich Manuscript. It has been compiled to be a machine readable version of the Voynich Manuscript based on transcriptions from various transcribers. Each transcription has been translated into the European Voynich Alphabet (EVA). An example of the archive in EVA and the corresponding text within the Voynich Manuscript can be seen within the appendix section A.3. The EVA itself can be seen within appendix section A.4.

Aim

The aim of the project is to determine possible features and relationships of the Voynich Manuscript using statistical methods that can be used to aid in the investigation of unknown languages and linguistics. It is not to fully decode or understand the Voynich Manuscript itself. This outcome would be beyond excellent but is unreasonable to expect in a single year project.

Motivation

The project shall attempt to find relationships and patterns within unknown text through the usage of known statistical methods on languages and linguistics. The Voynich Manuscript is a prime candidate for this as there is no known accepted translations of any part within the document. The relationships found can be used to verify the statistical methods and also be used to conclude on specific features of the unknown language(s) within the Voynich Manuscript.

Knowledge produced from the relationships and patterns of languages and linguistics can be used to further the current linguistic computation and encryption/decryption technologies of today [5].

Significance

There are many computational linguistic and encryption/decryption technologies that are in use today. As mentioned in section 1.3, knowledge produced from this research can help advance these technologies in a range of different applications [5]. These include, but are not limited to, information retrieval systems, search engines, machine translators, automatic summarizers, and social networks [5].

Particular technologies, that are widely used today, that can benefit from the research, include:

• Turn-It-In (Authorship/Plagiarism Detection)
• Google (Search Engines)
• Google Translate (Machine Runnable Language Translations)

Approach

The project has been broken down into several phases where each phase will be considering a specific feature of the Voynich Manuscript and/or linguistics while building onto what was learned in the previous phase(s). Many techniques may replicate previous research. The results within these documents will be used to compare and complement results obtained throughout the life of the project.

All phases will be coded and will therefore include testing as all code must be verified for results to be considered accurate.

Code shall be written in C++ and MATLAB languages as the project members have experience using these programming languages. MATLAB, in particular, is chosen as it provides a simple, easy to use mathematical toolbox that is readily available on the University systems. Other programming languages may be used if it is found to be more suitable.

BASH scripts have also been used for fast sorting of the Interlinear Archive files.

Completion of each phase is considered a milestone.

Phase 1 - Characterization of the Text

Characterization of the text involves determining the first-order statistics of the Voynich Manuscript. This first involves pre-processing the Interlinear Archive into a simpler machine-readable format.

The pre-processed files are then characterized through MATLAB code by finding and determining:

• Unique word tokens
• Unique character tokens
• Frequency of word tokens
• Frequency of character tokens
• Word token length frequency
• Character tokens that only appear at the start, end, or middle of word tokens

A 'unique' token is considered a token that is different than any of the other tokens. In terms of character tokens, difference is attributed to the token itself being visually (machine-readable) different than another. In terms of word tokens, difference is attributed to the structure of the word.

Resulting statistics can then be compared with other known languages through using the same code on the various translations of the Universal Declaration of Human Rights. Unfortunately the Universal Declaration of Human Rights is, by comparison, a small document which will limit results. However it will give a basis for follow-up research into the languages that have a possible relationship to the Voynich Manuscript based on the first-order statistics.

Further research can be carried out using any languages that appear to have a relationship to the manuscript through the compilation of much a larger corpus.

Phase 2 - English Investigation

The English investigation looks into the elementary structure of English text. It specifically examines the representation of the English alphabet and how the alphabetical tokens can be extracted from an English text using statistics. This is done to grasp a better understanding on how character tokens are used within text and how data and statistics relating to these character tokens can be used to characterize each token.

Initially, a corpus of English texts (see Appendix section A.9) shall be passed through the characterization code of phase 1 to determine the first-order statistics of each text. These will be compared to grasp a basic understanding of how each of the tokens can be statistically represented and how these statistics differ between texts. These tokens include alphabetical, numerical, and punctuation tokens.

The characterization code will then be expanded upon to include character token bigrams to further define the differences between character tokens. Bigrams give the conditional probability, P, of a token, Tn, given the proceeding token, Tn-1. This is given in the following formula:

P(T_n│T_(n-1) )= (P(T_(n-1),T_n))/(P(T_(n-1)))

It is expected that the probability of the different tokens along with the first-order statistics, obtained through the phase 1 code, will show definitive differences between alphabetical, numerical, and punctuation tokens.

Code will be written that takes these statistical findings into account to attempt to extract the English alphabet from any given English text with no prior knowledge of English itself. This will be used to examine the Voynich Manuscript to search for any character token relationships.

Phase 3 - Morphology Investigation

Morphology deals with the structure of the words, particularly the meaningful segments that make up a word [17]. Specifically, phase 3 will be looking into the possibility of affixes within the Voynich Manuscript.

As described in section 2, previous research has found the possibility of morphological structure within the Voynich Manuscript [2]. A Minimum Description Length model [12] may be used to attempt to segment word tokens into possible affix models.

The basis of the code will be examining word tokens within the Interlinear Archive and attempting to find all similar tokens. This will initially determine if a word token appears within another, different word token. Following the Minimum Description Length model, the code will then attempt to find the most compact representation of the word token and any pre or post word tokens.

By analysing the word tokens that appear within other word tokens, and their placement within said word tokens, it is expected that a hypothesis for possible prefix, affix, and stem word tokens will be concluded.

Coding this model into MATLAB will allow for use on the Interlinear Archive. The code will also be used on English texts to provide a qualitative comparison on the effectiveness and limitations of the algorithm.

Phase 4 - Illustration Investigation

The illustration investigation looks into the illustrations contained in the Voynich Manuscript. It will examine the possible relation between texts, words and illustrations. The different sections in the Voynich Manuscript are based on the drawings and illustrations in pages. Almost all the sections are texts with illustrations except recipes section.

In Phase 4, the basis of the code will be achieving the following functions:

• Finding unique word tokens in each pages and sections
• Determine the location of a given word token
• Determine the frequency of a given word token

The resulting statistics from the code can then be used into investigation. However, it should be noted that the manuscript may have been written by multiple authors and in multiple languages [13]. Sections of the manuscript will need to be investigated separately, particularly those written in different languages, along with the manuscript as a whole.

Phase 5: Collocations

Collocations have no universally accepted formal definition but deals with the words within a language that co-occur more often than would be expected by chance. Natural languages are full of collocations and can vary significantly depending on the metric, such as length or pattern, used to define a collocation.

In this research experiment, the definition used for a collocation is that of two words occurring directly next to each other. As collocations have varying significance within different languages, by extracting and comparing all possible collocations within the Voynich Manuscript and the corpus, a relationship based on word association could be found or provide evidence of the possibility of a hoax.

Resources

• Standard University Computers
  • MATLAB Computing Environment
  • C++ Programming Language
  • BASH Scripts
• Electronic Voynich Transcriptions
• Universal Declaration of Human Rights in various languages
• Various electronic English texts

Further Project Information

• Cracking the Voynich Code 2015

References

[1] D. Stolte, “Experts determine age of book 'nobody can read',” 10 February 2011. [Online]. Available: http://phys.org/news/2011-02-experts-age.html. [Accessed 12 March 2015].

[2] S. Reddy and K. Knight, “What We Know About The Voynich Manuscript,” LaTeCH '11 Proceedings of the 5th ACL-HLT Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, pp. 78-86, 2011.

[3] G. Landini, “Evidence Of Linguistic Structure In The Voynich Manuscript Using Spectral Analysis,” Cryptologia, pp. 275-295, 2001.

[4] A. Schinner, “The Voynich Manuscript: Evidence of the Hoax Hypothesis,” Cryptologia, pp. 95-107, 2007.

[5] D. R. Amancio, E. G. Altmann, D. Rybski, O. N. Oliveira Jr. and L. d. F. Costa, “Probing the Statistical Properties of Unknown Texts: Application to the Voynich Manuscript,” PLoS ONE 8(7), vol. 8, no. 7, pp. 1-10, 2013.

[6] S. Chakrabarti, M. Ester, U. Fayyad, J. Gehrke, J. Han, S. Morishita, G. Piatetsky-Shapiro and W. Wang, “Data Mining Curriculum: A Proposal (Version 1.0),” 12 April 2015. [Online]. Available: http://www.kdd.org/curriculum/index.html.

[12] J. Goldsmith, “Unsupervised Learning of the Morphology of a Natural Language,” Computational Linguistics, pp. 153-198, 2001.

[13] P. Currier, “New Research on the Voynich Manuscript: Proceedings of a Seminar,” 30 November 1976. [Online]. Available: http://www.voynich.nu/extra/curr_main.html.

[17] M. Aronoff, and K. Fudeman, “What is morphology,” Vol. 8., John Wiley & Sons, pp. 1-25, 2011.

Back

• Projects Main Page