Foreign Language Processing

With many of the S&P 500 companies now receiving over half of their revenues from foreign markets, the ability to properly handle foreign languages is an absolute must. At Ignited, we have extensive experience handling double-byte (pictorial) languages which are becoming more common in cases involving patent infringement and other intellectual property matters.

What is character encoding?
Character encoding defines the way that computers display and print information correctly. There are many encoding formats (examples include UTF-8 / UTF-16, JIS, SHIFT-JIS, ISO-2022) and without knowing the correct format, the viewer will see gibberish. For example, when reviewing a MS Word document that contains a foreign language, you are often prompted to select the encoding of the document. If you select the incorrect encoding, you will see symbols such as ?? or ??.

Language Detection At Ignited, we understand the importance of identifying a document’s character encoding. We have developed software that detects a document’s encoding and by doing so, identifies the primary language. This information can be very helpful when planning and structuring your review approach. For instance, your case team may wish to either contract foreign language reviewers or decide to translate particular languages prior to conducting a document review.

What review platform do I need to view these documents?
A handful of the most popular litigation review tools are now able to display double-byte characters, however not all have the capability. It is important to pick a tool that cannot only view the extracted text in these native languages, but also include specialized dictionaries and tokenizers to determine word and phrase breaks for proper search capabilities.

At Ignited, we offer two industry-leading online review platforms, Relativity and Catalyst. Both platforms allow users to rapidly search and review documents in over 70 major languages in a simple and secure environment. This means users can work with multi-lingual documents without the need to set up separate repositories for each language, run parallel queries and reconcile the results. Please consult your Account Executive to learn more about each tool and which may best suit your specific case requirements.