Advanced leveraging translation memory

Advanced Leveraging Translation Memory (ALTM) is the result of combining ‘statistical analysis and linguistic intelligence tools to create a new category of fuzzy matches that can lead to significant increases in translation productivity’.

The TAUS data association refers to ALTM as the new generation of Translation Memory (TM), because it identifies sub-sentence repetitions. Further in a recent report, TAUS determined that ALTM technology finds up to 30% more repetitions in a given document than a Conventional TM.

History

The concept behind translation memories is not recent — university research into the concept began in the late 1970s, and the earliest commercializations became available in the late 1980s — but they became commercially viable only in the late 1990s. In 2001, MultiCorpora released the first next generation Translation Memory (ALTM) tool. ALTM was initially coined “Textbase TM”. Since its release other companies have created similar next-generation products (see Current ALTM Products below).

How does a TM Work?

TM systems transform inventories of past translations, which may be scattered across organizations, into formats that can be easily located and reused. Generally, TMs scan entire repositories of previously translated documents and create a database by automatically extracting and aligning the source sentences with the target language sentences.

Conventional TM versus ALTM

Unfortunately, Conventional TMs generate less than perfect alignments; reducing the overall effectiveness of past translations for re-use. Conventional TMs also require a lot of maintenance to manually validate and correct misalignments because conventional TMs fracture entire documents to create a simple database of pre-aligned sentences taken out of context.

ALTM Differentiators

Granularity – ALTM technology features full-text indexing capabilities which allow users to search and retrieve text strings of any length, such as full and fuzzy segments, paragraphs, terms, and even sub-segments.

Context - Context of past translations is particularly valuable when translating more complex documents with full paragraph styles. ALTM technology allows you to build entire repositories of raw indexed texts while keeping the context intact for an on the fly view of how ambiguous terms, sentences and even paragraphs were previously translated. By providing context during translation, ALTM technology acts as an extensive "by-example" dictionary, containing usage and style references for terms and expressions.

Automation - ALTM technology enables users to automatically create TMs faster and with a higher alignment success rate than a Conventional TM. This not only saves the user the time, but it increases the effectiveness of the TM at identifying repetitions.

Current ALTM Products