Planned intervention: On Wednesday June 26th 05:30 UTC Zenodo will be unavailable for 10-20 minutes to perform a storage cluster upgrade.

There is a newer version of the record available.

Published September 10, 2022 | Version 1.4
Software Open

HeLI-OTS 1.4

  • 1. University of Helsinki

Description

HeLI off-the-shelf language identifier with language models for 200 languages.

Usage:
java -jar HeLI.jar -r <infile> -w <outfile>

The program will read the <infile> and classify the language of each line as one of the 200 languages it knows
and writes the results, one ISO 639-3 code per line, into file <outfile>.

You can use the -c option to make the program print a confidence score for the identification after each language code.

Usage:
java -jar HeLI.jar -c -r <infile> -w <outfile>

You can give the list of comma-separated ISO 639-3 identifiers for relevant languages after -l option.

Usage:
java -jar HeLI.jar -r <infile> -w <outfile> -l fin,swe,eng

You can give the number of top-scored languages to print after the -t option. (overrides confidence)

Usage:
java -jar HeLI.jar -r <infile> -w <outfile> -l fin,swe,eng -t 2

If you omit both of the filenames, the program will read the standard input one line at a time and write the result to standard output.

It can identify c. 3000 sentences per second using one core on a 2021 laptop and around 3 gigabytes of memory.

If you use this program in producing scientific publications, please refer to: 
 @inproceedings{heliots2022,
     title = "{H}e{LI-OTS}, Off-the-shelf Language Identifier for Text",
     author = "Jauhiainen, Tommi  and
       Jauhiainen, Heidi  and
       Lind{\'e}n, Krister",
     booktitle = "Proceedings of the 13th Conference on Language Resources and Evaluation",
     month = june,
     year = "2022",
     address = "Marseille, France",
     publisher = "European Language Resources Association",
     url = "http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.416.pdf",
     pages = "3912--3922",
     language = "English",
 }

Producing and publishing this software has been partly supported by The Finnish Research Impact Foundation Tandem Industry Academia -funding in cooperation with Lingsoft.

Files

LanguageModels.zip

Files (451.1 MB)

Name Size Download all
md5:d473630e6ef3d4fcac523c84b9ca489d
1.3 kB Download
md5:4ae98cac36248e8597a59aef81e98f18
6.0 kB Download
md5:447a3fef9d2876f5ba2df98179242df1
6.8 kB Download
md5:8235468bc8836d50c248111c86f389c6
6.5 kB Download
md5:a6972d15bb26e2da150aa209d7928660
575 Bytes Download
md5:4747a7cd42aa7fcd6e77fb56795878e0
219.3 MB Download
md5:de902339f6124186dcccde765811a12b
15.2 kB Download
md5:cc7aac3bbeaee30a070ad7fad3d609c0
115.1 MB Download
md5:b37aebb0ca12b7e05626c64f967e30a5
26.0 kB Download
md5:a9df4cd7b4b8b1238d3b81808f3fc8b7
39 Bytes Download
md5:f44bcfe8a8a8108095b6bc35cea8e31d
884 Bytes Download
md5:7a8d581f71b2740ab1689452c2da3c73
44.1 MB Preview Download
md5:bb0ae3b700049fd806e2a043e01265d6
11.4 kB Download
md5:cada4633f7ce1f00842477b6ed6f04d9
2.7 kB Preview Download
md5:fa3de39cf2e93085759e3f97cb9f4d0f
1.0 kB Download
md5:5d551dcb80653aaac5ecebae98842826
745 Bytes Download
md5:4d61698d70345bd4d8b87df4e086c37d
72.5 MB Download

Additional details

References