|
Title
|
|
|
|
Heimdall: In-line Language Identification Tool
| |
|
Author
|
|
|
|
| |
|
Abstract
|
|
|
|
| Heimdall is an open-source tool, written in Python, that searches a text for sequences written in other languages than the main one. Heimdall's roots in historical linguistics are reflected in the language models it is shipped with: its three default languages are medieval Latin, Early Modern French and Early Modern English. The tool is compatible with plain text files as well as xml-files. In the first case, it simply outputs a list of all foreign passages. In the second, it also allows you to tag the foreign passages directly in the input documents. |
| |
|
Language
|
|
|
|
English
| |
|
DOI
|
|
|
|
10.5281/ZENODO.3621420
| |
|
Full text (Publisher's DOI)
|
|
|
|
| |
|