Inventus Blog

Inventus is a leading international eDisclosure management practice, focussed on reducing ligation costs through a suite of bundled, best-of-breed technologies.

It's all Belgian Fries to Me: The Art of Multilingual eDisclosure (Part II)

Posted 06/11/19 7:00 AM by Jérôme Torres-Lozano


Inventus’s resident linguist, Jérôme Torres Lozano, continues to explore in this second and final part of the series - “It’s all Belgian Fries to me… or The Art of Multilingual eDisclosure” - the evolution of multilingual document processing and review by cleverly balancing the use of emerging technologies and human resources.

-> Missed Part I? Click here to read it!


Audio review: An added wrinkle in multilingual eDiscovery


When we thought we had foreign language documents covered, audio recordings started to be an increasing and substantial part of any regulatory investigation, especially in heavily regulated industries like finance and insurance. This meant that once again the eDiscovery specialists had to find ways to process this new format to allow for it to be processed, indexed, searched and listened to in the context of legal proceedings.


Technology existed that did part or all of that, with varying degrees of success, used by law enforcement, the military, intelligence agencies and, (un)surprisingly, the call center industry. Over time, audio processing software based on voice-to-text or phonetic speech technology was adapted to the needs of legal review with cool features like a silence detector that would eliminate no-speech sections to save on review time and costs or background noise reduction to improve the quality of the recording.


If the handling of written text in multiple languages was a difficult beast to tame, audio recordings in multiple variants of spoken language is one that is still hard to master. It reminds me of a Spanish case were I needed to search for the mention of an elusive ‘Mr Smith’ and as a linguist I had to think of all the ways a native Spanish speaker would pronounce this quintessentially English surname in Castilian or any of the Latin-American Spanish variants. Smith, EH-Smith, SmiT, EH-SmiT, Smiss, EH-Smiss, EH-Smiz… and we found passages mentioning Miss-TeRR EH-Smith! Music to my ear! 


Translation methods for electronic discovery


Now, what do you do with all of these documents that are in so many different languages? Translate them, machine translate them, or have them reviewed by a native-speaking lawyer? There are, in fairness, no right or wrong answers — it all depends.


Machine translation has come a long way and while it is said that in the early days some maverick providers used tools available online to machine translate documents, therefore sending their client data out onto the Internet, most serious outfits used in-house hosted hybrid solutions based on tried and tested, thought-limiting, rule-based and statistic translation technology.


The latest development is neural machine translation, a predictive model that takes into account full sentences or paragraphs rather than a sequence of a few words, and "learns" the nuances in languages based on that specific language’s morphology and characteristics — thus achieving higher levels of quality.


Soon enough, this was adopted at large in the eDiscovery world.


Technology-based translation is a valuable tool to prioritize documents and give you high-level insight into the content of the documents at a fraction of the cost of human translation. But if you need to provide a translation to the court or the other side, a certified human translation will often be the standard. From my translation industry days, the golden rule was to use translators that would translate into their mother tongue. This is still valid today, as translators will always have a more profound linguistic and cultural attachment to their mother tongue than the source language however well they understand it, speak it, and write it.


Another solution that bypasses these solutions or is used in combination is the increasingly popular use of native or language-proficient document reviewers. Qualified lawyers that will have the necessary language and industry-specific skills to perform a first-level review of the document population obviating the need for expensive translation, whether human or machine, of documents that needn’t be translated in the first place. Most contract lawyers are proficient in several different languages which befits our modern multilingual world, provides further flexibility, and increases the speed of review.


It's a full circle!


I would not have thought that 15 years after leaving the translation industry, now working in the realm of legal technology, I would be the resident linguist assisting corporations and law firms with their multilingual eDiscovery needs, whether it be speaking to the clients’ IT representatives in their own language, breaking cultural barriers explaining the process of discovery in layman’s terms, or analyzing audio recordings and strategizing on the best search methodology to apply when dealing with other languages. La boucle est bouclée!*


* The circle is complete!


(Missed Part I? Read it here!)


Want to learn everything you need to know about conducting multilingual eDiscovery? Join us for a free webcast on July 16! Multilingual legal experts will share best practices for conducting international discovery projects, choosing the right translation methods, and share real-life case studies of what's worked - and what won't. Click below to register!

Register Now


Jérôme Torres-Lozano

About The Author

Jérôme Torres Lozano is Legility’s Director of Professional Services based in London. Jérôme has more than 15 years’ experience in eDisclosure and computer forensics. He established computer forensics divisions, led global eDiscovery project management teams, and advises clients around the world on all technical and workflow aspects of their eDisclosure needs. He speaks French, Spanish, English, Italian, Dutch, and Portuguese.


Reduce overall cost and risk of your entire legal process
Learn More