How Neural Machine Translation can aid the e-discovery process

How Neural Machine Translation can aid the e-discovery process

Neural Machine Translation (NMT) is a hot topic these days. But what role can it play in identifying, collecting, and producing electronically stored information (ESI) in e-discovery? How exactly can it benefit law firms, e-discovery service providers, and end-clients? 


We are already seeing Machine Translation (MT) being used in new ways aside from its “traditional” use in post-editing workflow. More and more frequently this includes cases where large volumes of multilingual content need to be turned around quickly, such as e-discovery and cross-border litigation, and regulatory compliance.

The e-discovery process is often complicated because of the sheer volume and variety of electronic data produced and stored. ESI can come in all sizes and formats including, but not limited to, emails, databases, voicemails, video files, and documents. Preserving the original content and metadata for ESI is crucial to avoid claims of corruption or evidence tampering later in the litigation process.

In cross-border discovery, MT plays a vital role. In these cases, the ESI is almost always presented in a language which both parties may not have an understanding of, or in cases involving large multinational corporations, it may include many language variations. Between different language types and unpredictable file formats, the entire operation can become very complex.

Reviewing documents in native languages is possible but requires hiring attorneys who are fluent across multiple languages – an expensive process. Human translation is also quickly ruled out as an expensive and time-consuming process, and, given the pure volume of data which is also presented, often human translation is simply not practical.

With court dates looming, MT often quickly becomes the only viable option. In these cases the translation doesn’t even need to be perfect – it merely needs to be adequate enough to allow the attorney to determine whether the document contains relevant information and is worthy of a second look, or a full professional translation.

With the recent intrigue surrounding Neural Machine Translation (NMT) it is natural to ask what role it may play in the process of e-discovery.

Artificial Intelligence in Translation

The optimism surrounding initial performances of Neural MT is driven by findings that it can almost perform on par with existing technologies out of the box, and, for languages that have traditionally proved harder for MT such as Japanese, Korean, and Arabic, Neural MT is showing really promising results. Things are likely to really get interesting over the next few years as we gain clarity around how Neural MT is working and begin to see new types of hybrid technology that include machine learning and neural approaches.

Of course, translation alone is not enough and must be coupled with other technologies such as automated language identification, because it’s often not known what languages might be encountered in ESI.

At the end of the day, the goal of e-discovery is to find relevant documents. In this regard, translation is not a destination, but rather a detour on the way. The MT step must be as fast, effective, and as seamlessly integrated as possible to faciliate document review. With Neural MT, we are well on the way to achieving this.

Find out more information about Iconic’s e-discovery solution here:

Here at Iconic we are excited to be incorporating NMT in cases where it can provide a real benefit. Keep tuned to in the coming weeks for some case studies reflecting this! 

About Iconic Translation Machines

Iconic Translation Machines is a leading machine translation software and solutions provider who specialise in custom solutions tailored with subject matter expertise for specific industry sectors including eDiscovery, legal, life sciences, and financial services. Iconic is the MT partner of choice for some of the world’s largest translation companies, information providers, and government and enterprise organisations, helping them to translate more content, more accurately and in less time, resulting in significant cost savings and increased revenue. Iconic is based in Dublin, Ireland.

Thank you, your sign-up request was successful! Please check your e-mail inbox.
That email address is already subscribed, thank you!
Please provide a valid email address.
Oops. Something went wrong. Please try again later.


Comments are closed.

WordPress Lightbox Plugin
Get Started