memoQ blog

Using TaaS for Terminology Extraction

Peter Reynolds
Peter Reynolds - 14/04/2014

3 minute read

TaaS (Terminology as a Service) is a new and innovative terminology management platform. This will be integrated in memoQ 2014 which will be released in June. However, you can start using this service immediately. One of the powerful things to use on the TaaS platform is language aware terminology extraction. With TaaS it is possible to add a document, get the terms extracted and matched with your desired target language.

You can start using TaaS immediately for free and it is your decision whether to share your terminology and with whom to share it.
 
You can find the TaaS platform at  https://demo.taas-project.eu.


 

To sign up for TaaS simply click on the Log in/ Sign up button on the right hand side of the webpage. You then just have to enter a user name, email addresses and password. Then you can log in. If you have already worked with TaaS you will see a list of your projects once you log in.
 


 

To create a new project Click on the Create Project button to be found on the top right hand of the page.

You must enter a name of the project, source language, target language and domain. You can also add a description, product name, customer name and business unit.


 

When the project is created you will see the tabbed project space with the tab for documents highlighted. You can just drag and drop the document you want to add or click Add Documents.

In the Extraction tab you can select the term extraction functionality you wish to use. For this example I have used the language aware TWSC tool. TWSC stands for Tilde wrapper system for CollTerm. TWSC is based on linguistic analysis (part of speech tagging, morpho-syntactic patterns etc.) enriched by statistical features (e.g., frequency score). It is also possible to use our language independent term extractor. This is similar to the one which is currently available within memoQ.

After the term extraction is done you will get a list of source terms extracted from your document. The tool will also automatically check if the term previously appears in the IATE or EuroTermBank termbases and present the translated term as well.
 


 

Another wonderful feature in TaaS if the visualisation tool. This allows you to look at your document and see the terminology in context.
 


 

You now have a list of candidate source terms, and in some cases target terms. You can edit this and store in your own termbase on TaaS. This can be then used by you alone, shared with some colleagues or made public.

You can also export the termbase and use elsewhere. TaaS is a very rich set of terminology management functionality. This blog post deals with just terminology extraction but with TaaS you have a very powerful terminology platform for free. I would recommend you signing up and start using it.

Peter Reynolds

Peter Reynolds

memoQ co-CEO

Browse all posts