About this blog

Translator's Shack is a collection of links, news, reviews and opinions about translation technologies. It's edited and updated by Roberto Savelli, an English to Italian translator, project manager and company owner of Albatros Soluzioni Linguistiche, a team of English-Italian translators, which hosts and supports this blog.

The Life as a PM category, managed by Gabriella Ascari, contains topics that are less technical in nature, but which we're sure will be appreciated by owners of small translation businesses and freelancers.

Here are links to my pages on some social networks:

Highly recommended:

Dynamic Translation Memory: Using Statistical Machine Translation to improve Translation Memory Fuzzy Matches

I came across this interesting paper by Ergun Biçici 1 and Marc Dymetman. In short:

The paper proposes to perform this automation in the following  way: a phrase-based Statistical Machine  Translation  (SMT)  system (trained on  a  bilingual  corpus  in the same domain as the TM) is combined with the TM fuzzy match, by extracting from the fuzzy-match a large (possibly gapped) bi-phrase that is dynamically added to the usual set of “static” bi-phrases used for  decoding the source.

Here is the download link

Some news from Terminotix


Yesterday I received the latest edition of the LogiTerm newsletter. You can download it here. There are some interesting announcements:

  • Agreement with SYSTRAN:
    Terminotix has entered into an agreement with SYSTRAN to  add  machine  translation  solutions  to  the  Terminotix product  line.
  • YouAlign completely free:
    YouAlign, the   text   alignment   website   launched   by Terminotix in August 2009, was supposed to be free for a limited time only, but is now completely free. YouAlign lets you  quickly  and  easily  create  HTML  bitext  and  TMX translation memory files from pairs of input files. Bitext and translation  memory  files  generated  by  YouAlign  can  be downloaded for use with bilingual full-text search engines and translation memory systems. No software to install — everything  is  done  through  your  web  browser.
  • SynchroTerm 2010 released:
    The 2010 release of SynchroTerm, the powerful bilingual term extraction program, is now available. Enhancements include  optimized  memory  use  for  handling  larger  files; support  for  Greek,  Dutch,  Hungarian,  Norwegian,  Polish and Turkish;

TAUS: What you don’t (want to) know [about Google Translation Toolkit]

Jaap van der Meer of TAUS (Translation Automation User Society) says in his recent post about Google Translation Toolkit:

Translators using the Translation Toolkit ‘share’ their translations with Google. If 100,000 translators start using the service, Google will be harvesting 50 billion words of good quality translation data per year to help Google improve their automatic translation engines. In addition translators may be uploading their own (or their customers’) TMs.

Read the ret of the post at the URL below:
Google Translation Toolkit | Technology.

Google Translator Toolkit

This link came through Twitter this morning. Google has taken one more step towards implementing a web-based translation environment that supports both human and computer-generated translations. Here is a brief description from Google Translator Toolkit Help:

Google Translator Toolkit is part of our effort to make information universally accessible through translation. Google Translator Toolkit helps translators translate better and more quickly through one shared, innovative translation technology.

Here’s what you can do with Google Translator Toolkit:

  • Upload Word documents, OpenOffice, RTF, HTML, text, Wikipedia articles and knols.
  • Use previous human translations and machine translation to ‘pretranslate’ your uploaded documents.
  • Use our simple WYSIWYG editor to improve the pretranslation.
  • Invite others (by email) to edit or view your translations.
  • Edit documents online with whomever you choose.
  • Download documents to your desktop in their native formats — Word, OpenOffice, RTF or HTML.
  • Publish your Wikipedia and knol translations back to Wikipedia or Knol.

How is this different from Google Translate? Google Translate provides ‘automatic translations’ produced purely by technology, without intervention from human translators. In contrast, Google Translator Toolkit allows human translators to work faster and more accurately, aided by technologies like Google Translate.

Here’s a 1 1/2 minute YouTube video that illustrates the main features.

Google Translator Toolkit basics

Microsoft Translator: machine translation for Microsoft Office documents

The Microsoft Research Machine Translation (MSR-MT) Team Blog has published some details about a translation plug-in for Microsoft Office.

Now you can translate your Microsoft Office documents with Microsoft Translator – right within Office! You can translate words, phrases, or even your entire document, through the Research task pane. We blogged about setting this up manually for Office 2007 or Office 2003 previously – now it’s really easy!

This works for both Microsoft Office 2003 and 2007. The current default in Microsoft Office is WorldLingo – this installer will update your task pane to use Microsoft Translator as the default translator for the languages we provide.

Download the installer now and let us know what you think over in the Forum!

Via Microsoft Research Machine Translation (MSR-MT) Team Blog

TranSphere hybrid machine translation system for Windows


AppTek, a developer of software for human language technology, has completed its hybrid machine translation (HMT) system for both Windows server and 32-bit Windows for PC. AppTek’s TranSphere HMT system is a full integration of statistical and rule-based methodologies.

Via MultiLingual Computing, Inc., News

SpeechTechMag.com: AppTek Launches Hybrid Machine Translation Software

image The Speech Technology Magazine contains an article about AppTek’s hybrid machine translation software. Here’s a brief excerpt:

According to Hassan Sawaf, chief scientist at AppTek, the company’s hybrid model is unlike any other system on the market today—a fact that has lead some universities to attempt to copy the hybrid model.

“Even if companies attempt to hybridize they only do hybridization insofar as that they basically combine translation memory with machine translation,” he says. “Hybridization like we do and a tight integration of rule-based features and statistical-based features are unique.”

AppTek’s HMT solution provides a full integration of both methodologies instead of simply adding rules to the statistical system or a minor statistical module to the rule-based engine.

SpeechTechMag.com: AppTek Launches Hybrid Machine Translation Software

Global Watchtower – Article on rule-based machine translation

The Global Watchtower blog contains a post about recent developments in rule-based MT.

For a brief overview of rules-based MT as opposed to its competing technology, statistical MT, about the differences between the two approaches and why they might matter to technical translators, see also the following Wikipedia links: More »

LTD Newsletter 4/2008 is Out

ATA’s Language Technology Division Newsletter issue 4/2008 is available. Here are the featured articles:

Can I Remove a Word from Office’s Speller Dictionary?, by Thierry Fontenelle
If you ever wanted to improve Office’s spell-checker, here are some suggestions for you.

ATA Language Technology Division Annual Meeting Minutes taken by Laurie Gerber.

Trados Tip, by Tuomas Kostiainen
Tuomas reminds us that MultiTerm is part of the Trados package and should not be forgotten.

Sil Converter: A Freeware, Universal World Font Converter, by Ravishankar Shrivastava
Glimpse into the world of pre-Unicode font conversion – and why it is still relevant today.

The Continuing Evolution of Automated Translation Technology: RbMT vs. SMT, by Kirti Vashee
A look at the two main approaches to machine translation.

via LTD News » Newsletter Archive.

Twitter (semi-)automated translation

The following site offers machine translation of Twitter messages. What’s interesting about this service, at least on paper, is the fact that the user’s Twitter messages can be reviewed and edited by followers.

Worldwide Lexicon Twitter Translator

Translate your Twitter feed! We translate your tweets using machine translation, and your followers can edit or replace these translations to improve them.

via Worldwide Lexicon : Twitter Translator.