Terminology Extraction

Below you find a list of tools that can extract terminology from existing texts. These tools can automatically identify term candidates in corpora which can then be saved to a terminology database. While many tools support monolingual term extraction there are some tools in the list that can carry out multilingual term extraction. Many times extracted terms are supplied to the user in the form of a list, from which the language worker (terminologist, technical writer, translator etc.) should manually pick and confirm the term candidates for the terminology database. The tools listed below are sometimes part of a terminology management system. This list is subject to alteration and is not a comprehensive overview. The software has been reviewed in the versions available by the end of 2013.


Acrolinx

Acrolinx is a tool with many features and functions supporting the creation and maintenance of text content, including term extraction. Both mono- and bilingual extraction can be carried out using Acrolinx. Furthermore, using the "Batch Checker" terminology can be extracted from entire documentation projects. An optional add-on allows setting up a suggestion system for new terminology. More information can be found here.

Website

Acrolinx
Friedrichstrasse 100
10117 Berlin
Phone: +49 (030) 288 84 83 30
Fax: +49 (030) 288 84 83 39
This email address is being protected from spambots. You need JavaScript enabled to view it.


crossMining

Across offers several software solutions which enable the user to carry out term extractions. Firstly, crossMining, a component of the Across Language Server allows multilingual term extraction that can be carried out based on existing translation memories or terminology databases. Secondly, Across Language Server itself includes a function for monolingual extraction. Thirdly, crossAuthor Linguistic, the product targeted at technical writer also permits the extraction of terms. Finally, Across Personal Edition for freelance translators has a terminology management component called crossTerm which can be also be used for monolingual term extraction.

Website

Across Systems
Im Stoeckmaedle 13
76307 Karlsbad
Deutschland

Phone: +49 (0) 7248 925 425
Fax: +49 (0) 7248 925 444
This email address is being protected from spambots. You need JavaScript enabled to view it.


LogiTerm

LogiTerm is a translation memory system by the Canadian company Terminotix. Aside from a terminology management tool it also offers a feature for monolingual or bilingual terminology extraction.

Website

TERMINOTIX INC.
2053 Jeanne-d'Arc Ave
Suite 401
Montréal, Québec
H1W 3Z4
Canada
Phone: +1 514 989-9465
Fax.: +1 514 989-5005
Email: This email address is being protected from spambots. You need JavaScript enabled to view it.


memoQ

memoQ is a translation memory system by Kilgray. The full version also includes a terminology extraction function. Terminology can be extracted either from translation memories or from the LiveDoc database or from translation documents. The term extraction process produces a list of term candidates that can be reviewed by a language worker. More information on memoQ can be found at this section of our portal.

Kilgray Deutschland GmbH
In der Rosenburg
Rosenburgweg 49
53115 Bonn
Germany


SDL Multiterm Extract

MultitermExtract is an extraction tool by the company SDL. This tool is connected to the terminology management system Multiterm, i.e. it can only be used if the adequate version of Multiterm is installed on the computer. Extraction can be carried out monolingually or bilingually, the supported file formats include TMX, TMW and TXT. Following the term extraction process a list of term candidates is generated that can be edited by the user. More information on terminology management using Multiterm can be found here.

Website

SDL Munich
SDL Ltd. Zweigniederlassung für Deutschland
Auenstrasse 100
80469 Munich
Germany
Phone: +49 (0)89 24 291 201
Fax: +49 (0)89 24 291 159


STAR TransitNXT

The translation memory tool Transit NXT features a term extraction function. Monolingual extraction can be used for source texts. The extracted term candidates are compiled in a list for general terms. The language worker can move selected terms to a list for technical terms or choose to ignore term candidates. The technical terms list can be used to establish a new dictionary or complement an existing one within the Transit NXT environment. STAR also offers a terminology management system called TermStar NXT. More information on TermStar can be found here.

Website

STAR Germany GmbH
Dornierstraße 3
71034 Böblingen
Germany
Phone: +49 7031 21 70-0
Fax: +49 7031 22 72 30
Email: This email address is being protected from spambots. You need JavaScript enabled to view it.


TaaS - Terminology as a Service

TaaS is a joint project by the Cologne University of Applied Sciences, the University of Sheffield and the companies Tilde, Kilgray and TAUS. The aim of the project is the establishment of a sustainable cloud-based platform for terminology services. The platform allows monolingual terminology extraction and automatic recognition of translation equivalents. The tool provides a list of term candidates which can be edited by the user and exported in to TBS, TSV and CSV files. As of April 2014 the beta version of the platform can be found here.


Termflow

Termflow is a terminology workflow tool by Transline Deutschland GmbH. This web-based tool includes a terminology extraction function that supports PDF, XLF and TXT files. Term candidates can be exported into CSV and TBX file formats. A special feature is the interface for tools Across and Multiterm. As of April 2014 the company is working on more interfaces.

Website

Transline Deutschland GmbH
Am Heilbrunnen 47
72766 Reutlingen
Germany
Phone: +49 (0) 7121 9463-0
Fax: +49 (0) 7121 9463-150