New Term Extraction Features in InterpretBank and InterpretersHelp – Thumbs up!

Extracting terminology from preparatory texts into a term database seems to be the hot topic of the moment, judging by what the two most active and innovative CAI (computer-assisted interpreting) tools, InterpretBank and InterpretersHelp, are working on at the moment.  So while I am still waiting to become a Windows beta tester of Intragloss, the pioneer in this field, I am eager to have a go at both InterpretBank5’s (beta) and InterpretBank’s (experimental) new extraction features.

InterpretBank by Claudio Fantinuoli has been adding quite some time-saving features for conference preparation lately. Apart from searching online ressources on the go while building your glossary, it now promises to extract terminology from your glossaries, view original and translation in parallel and link documents to glossaries. This does indeed sound like Intragloss combined with the sophisticated booth-friendly terminology management system that InterpretBank has been for many years. So off we go!

As you can see in the picture, a new “documents” icon has been added to the familiar three others (editing, conference mode, flashcards). When I press the magic button, the documents pane appears in the bottom left corner and lets me add documents like pdf or pptx in my two languages and display them next to each other. Unfortunately, there is no synchronised scrolling and no search function to look up word in the documents, but these functions are to be implemented soon. The selected documents are now linked to the glossary, so whenever this particular glossary is opened, they will appear in the documents pane. Highlighting words in the two texts and inserting them into the glossary or looking up translations in my favourite online resources (like IATE, Linguee, Pons, LEO and others more) works so swiftly, when I first tried it the terms were in my glossary before I had even noticed.

For English texts, context examples can be looked up using the right mouse button or using the icon in the list of extracted terms.  And what’s great for sharing with colleagues and for using in the booth: The text can be opened in a separate window and annotated with records from the glossary:

Automatic extraction of terminology or key concepts so far only works for English, but will be implemented for other languages, too (German, Spanish, French and Italian are planned to be released in April). Quality of extraction, as always, depends on many factors, like the amount of text and the subject area, but it is good to get a first impression of the subject matter at hand.

InterpretBank as a locally installed application raises no confidentiality issues with your client’s documents being opened and processed, as everything InterpretBank does happens on your computer (unless you use the “send document to any device” option).

If you are more of a team glossary and online networking person, InterpretersHelp by Yann Plancqueel and Benoît Werner is the other option to manage glossaries and manually extract terminology from texts. It is quite straightforward: Adding documents works via Copy & Paste, you just paste the text into a field for the respective language so you have the two language versions displayed next to each other (but with no synchronised scrolling either). When I tried it, inserting 20 pages from a pdf worked fine. Words can be looked up in the texts using the browser search function.

The highlighting and inserting also works very swiftly and you can look up terms in Google Translate and the Oxford Dictionaries. Once you have extracted all the vocab you need, you press a button to add all the new entries to your glossary. When changing back from the glossary view to the extractor, the texts have disappeared.

InterpretersHelp as a cloud-based tool addresses the data protection issue by encrypting the data that transit to and from the website (https://interpretershelp.com/help/secure_hosting).

Of course there are zillions of other functions interpreters need for CAI tools to support their workflow perfectly. But I think that both InterpretBank and InterpretersHelp have added one super useful feature to make our lives easier. Thanks a lot!

About the author:
Anja Rütten is a freelance conference interpreter for German (A), Spanish (B), English (C) and French (C) based in Düsseldorf, Germany. She has specialised in knowledge management since the mid-1990s.

Further reading:

Summary Table of Terminology Tools for Interpreters. <www.termtools.dolmetscher-wissen-alles.de>

Josh Goldsmith: The Interpreter’s Toolkit: Interpreters’ Help – a one-stop shop in the making?. In: aiic.net February 12, 2018. <http://aiic.net/p/8499>.

Anja Rütten: InterpretBank 4 Review. 31 July 2017. <https://blog.sprachmanagement.net/interpretbank-4-review/>.

Alexander Drechsel: App profile: Interpreters’ Help. 2 Oct 2015. <https://www.adrechsel.de/dolmetschblog/interpretershelp>.

Anja Rütten: Booth-friendly terminology management revisited – two newcomers. 29 April 2014. <https://blog.sprachmanagement.net/booth-friendly-terminology-management-revisited-2-newcomers/>

 

 

 

 

 

 

 

Comments

3 responses to “New Term Extraction Features in InterpretBank and InterpretersHelp – Thumbs up!”

  1. Rodolfo Maslias avatar

    Shared on Fb page European Terminology

  2. Aude-Valérie Monfort avatar

    FEEDBACK ON THE INTEPRETBANK
    AUTOMATIC AI TERM EXTRACTION
    TO CREATE A GLOSSARY

    After two-year break, I thought I would give InterpretBank (IB) another try because
    a) the preparation for my next assignment involved a 130 page text document and
    b) I was curious about the latest AI developments of the programme, which have been announced everywhere.
    In order to take advantage of the new AI functionality, I first have to upgrade my licence and consider the various options available. I decide to purchase a monthly subscription for freelancers, which I can cancel at any time. The process of purchasing and installing version 9.40 is quick and easy.
    My goal is to extract the terminology from the large document as efficiently as possible, so I opt for automatic term extraction. The first improvement is that I can add a large PDF file by drag-and-drop and open it without any problem. It opens immediately and in a readable format (this was one of the reasons I had stopped using IB).
    At the same time, I open the documentation on the IB website, which is helpful but not quite up to date (the screenshots show an older version with different icons in a different part of the IB window). To be fair, developments happen so fast that I understand how difficult it must be to update the documentation in time.
    Note that the “Extract terms” icon is now placed below the “My Documents” frame, to the left of the “ParScroll” icon. The pop-up window shows several options:

    – Extract terms with Cloud AI
    – Create glossary with Claud AI
    – Extract terms with Confidential AI
    – Extract abbreviations with Confidential AI
    – Create glossary with Confidential AI
    – Extract key points with Confidential AI

    I have tested 3 of them.
    (For information, the following tests are performed on Mac OS Ventura 13.7.2 to create a 4 language glossary (EN-FR-DE-IT) from a 130 page PDF file in English.)

    Test 1: Create glossary with Cloud AI / with Confidential AI”
    IB extracts terms and translates them relatively quickly. Unfortunately, the system does not give you the number of glossary entries. With Cloud AI, I get 6 pages of entries, with Confidential AI, the number of pages increases to 31. With Cloud AI the entries are technical terms and some translations need to be checked or changed. With Confidential AI, the list includes E-VE-RY-THING, including articles and prepositions, all in capital letters, so not really useful.

    Test 2: Extract terms with Cloud AI
    Result: 10 pages with a total of 82 terms (120 on a second extraction run)
    The terms are extracted and can be processed, page by page of 10. Processing means inserting, searching in context in the document, marking as “not useful”, selecting for “insert into glossary” or “insert into glossary and translate”. The terms are in lower or upper case unless an acronym has been identified.

    Test 3: Extract terms with Confidential AI
    Result: 10 pages with a total of 596 terms.
    The terms appear in lower case unless an acronym has been identified. Once added to the glossary, they are all in lower case. In another extraction run, all terms are listed in capital letters.
    In all cases I have tested, once a term has been to into the glossary, it can be edited but not deleted.

    After the AI has extracted the terms, I have to go through the 596 and decide which ones to keep, which ones to translate, check them in context, see if they’re properly capitalized, if they’re really acronyms, etc. It is a slow and tedious process. When I click on the icon for “Search the term in the preparatory document to understand the context of use”, a separate window opens with several examples if the term occurs several times in the document. Good. Not so good is that I have to click the red button in the top left-hand corner of the window again before I can continue.To save time, I would prefer the window to close automatically when I select another term.
    It is possible to edit a single term by clicking on + (it is then inserted into the glossary mask and can be edited but cannot be deleted later). Alternatively, it is possible to insert several terms selected from the list and edit them later using the standard glossary editing function (pencil icon in the top right corner of the main IB window).
    If I choose “insert and translate”, the system will take a bit longer, inserting and translating each term at a time while I wait in front of my screen.
    There may be some shortcuts that I have not yet discovered. However, given that I only use IB sporadically, it would be hopeless to try to memorize shortcuts to the point where I could use them efficiently.

    My conclusion is this: While IB seems to have improved and become more stable, preparing for an assignment with the AI term extraction feature requires some extra screen time, with little or no cognitive benefit over what I usually get from preparing with my own speed reading and touch typing skills.

    1. Anja Rütten avatar

      Thanks, Aude-Valérie, for this valuable update!

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.