Tackling the Tower of Babel of Multi-Language Corporate Discovery

Do you know where in the world your company’s next legal matter will arise?


The possibilities are more far-reaching and less predictable than ever before, as businesses expand their operations and markets throughout the globe. Amid a complex international legal and regulatory environment,  businesses can face lawsuits in any number of forums and are subject to investigations by any number of government entities. Whether involving trade regulation, anti-corruption laws or licensing deals, that next legal matter could come from anywhere.

But while businesses cannot know from whence their next legal matter will come, they can be prepared for the discovery that inevitably will follow.

Preparation is critical because discovery in cross-border legal matters is a tricky business. Many factors make it tricky, from legal to cultural to technical, but a key factor is language. Global businesses communicate across many languages, both internally and externally. That means that discovery documents and emails also come in many languages. The discovery platform you use must have the ability to handle language-specific search, analysis and review.

In a series of posts here, we’ve been discussing the features of Insight Enterprise, Catalyst’s secure, centralized platform for corporate e-discovery, which was launched Jan. 10. Today’s topic is how Insight Enterprise helps corporations and their legal teams be prepared to work efficiently and effectively with multi-language documents.

Process and Index in Any Language

Catalyst was one of the first e-discovery companies to support multi-language discovery and that legacy continues in Insight Enterprise, starting with processing and indexing. The platform includes sophisticated language identification and word tokenization capabilities to ensure that multi-language documents are processed, searched and produced properly.

The processing engine used in Insight Enterprise was designed for complex multi-language documents. It not only handles Unicode but can also process and index non-Unicode documents, including documents using Asian-language encodings such as Shift JIS and Big5. Proper processing of multi-language documents is critical if their characters are to be properly displayed.

Also important with multi-language documents is proper tokenization. The problem with many Asian languages such as Chinese, Japanese and Korean, as well as with languages such as Hebrew and Arabic, is that they do not have spaces between words. Without spaces, a search engine is unable to index them and keyword searches produce inaccurate results.

Inisght Enterprise addresses this during the indexing process by identifying and tokenizing these languages. Its sophisticated tokenization system accurately and precisely separates characters into words so that searches of the documents will be accurate.

A further advantage of tokenization is that it allows the use of Insight Predict, Catalyst’s advanced technology assisted review engine. Through language identification and word tokenization, Insight Enterprise is able to go beyond English for advanced predictive analytics in hundreds of languages.

Search and Review in More Than 270 Languages

Insight Enterprise enables search across more than 270 languages with a single query, using a consistent query syntax. When you are searching in a language other than English, Insight allows you to Identify the specific language being searched for more accurate results.

Insight Enterprise also allows users to group documents by language for review. As documents are indexed, the system identifies a primary language, allowing review administrators to group and assign documents by language. This leads to more efficient use of often higher-priced multi-language reviewers.

Another feature is the ability to translate documents on the fly. With one click, you can translate documents from other languages into English or automatically assign documents for bulk translation. In addition, the Translation Assistant allows you to translate search terms from English into your target language.

If your team has questions about multi-language search, help is standing by. An Insight Enterprise license includes consulting from the Catalyst Professional Services group. Catalyst’s consultants are experts in multi-language search and analytics. They can help formulate and execute multi-language search strategies, making sure key variations of queries are considered. They have special expertise in the Asian languages and in strategies for reviewing and producing multi-language documents.

When your business is global, your discovery will be too. The best way to manage multi-language discovery and investigations is to be prepared with the right technology. Insight Enterprise helps you ensure that you are.



About Bob Ambrogi

Bob is known internationally for his expertise in the Internet and legal technology. He held the top editorial positions at the two leading national U.S. legal newspapers, the National Law Journal and Lawyers USA. A long-time advisor to Catalyst, Bob now divides his time between law practice and media consulting. He writes two blogs, LawSites and MediaLaw, co-authors Law.com's Legal Blog Watch, and co-hosts the weekly legal-affairs podcast Lawyer2Lawyer. A 1980 graduate of Boston College Law School, Bob is a life member of the Massachusetts Bar Foundation and an active member of the Massachusetts Bar Association, which honored him in 1994 with its President's Award.