# Knight 1999: A computational approach to deciphering unknown scripts

> Kevin Knight, Kenji Yamada, 1999. 1 records on Mysteries Department cite it. The book (chapter 22) cites it for the two-state hidden Markov model that…

Source: https://mysteriesdept.com/sources/SRC08JJ1VTG41RF/a-computational-approach-to-deciphering-unknown-scripts  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Sources](https://mysteriesdept.com/sources)[Voynich Manuscript](https://mysteriesdept.com/mysteries/voynich-manuscript)Knight 1999

**0**

# A computational approach to deciphering unknown scripts

Kevin Knight, Kenji Yamada, 1999. _Proceedings of the ACL Workshop on Unsupervised Learning in Natural Language Processing_: 37–44.

An early paper treating the decipherment of unknown scripts as a statistical learning problem, recovering sound values for written symbols with the EM algorithm in tests on known languages.

**Voynich Manuscript** ArticleChecked against the original0

## What it's used for here

The book (chapter 22) cites it for the two-state hidden Markov model that separates vowels from consonants without being told which is which.

## Cited by on this site 1 record

[Reading Without a Key](https://mysteriesdept.com/sources/SRC0D8NJAWT22V4/reading-without-a-key)

The book, version 2.0

SRC

## Cite it

```
Knight, K., & Yamada, K. (1999). A computational approach to deciphering unknown scripts. Proceedings of the ACL Workshop on Unsupervised Learning in Natural Language Processing, 37–44.
```

[Read it free at aclanthology.org](https://aclanthology.org/W99-0906/)[PDF stored here · 8 pages](https://mysteriesdept.com/sources/SRC08JJ1VTG41RF/a-computational-approach-to-deciphering-unknown-scripts/pdf)

The PDF is the copy aclanthology.org gives away, kept here so the link can't break. Downloads are open to beta members.

Key

**SRC** 08JJ1VTG41RF

Kind

Journal article

Rights

CC-BY-NC-SA-3.0

Checked

Against the published article

Added by

[apollo](https://mysteriesdept.com/u/apollo)

The record

Bibliographic records are CC0. Take this one as CSL-JSON, BibTeX or RIS.

[CSL-JSON](https://mysteriesdept.com/sources/SRC08JJ1VTG41RF/a-computational-approach-to-deciphering-unknown-scripts/csl.json)