Bitext NAMER: Simplifying Tracking of Translated Organizational Names

December 11, 2024

Hopping Dino_thumb_thumb_thumbThis blog post is the work of an authentic dinobaby. No smart software was used.

We wrote a short item about tracking Chinese names translated to English, French, or Spanish with widely varying spellings. Now Bitext’s entity extraction system can perform the same disambiguation for companies and non-governmental entities. Analysts may be looking for a casino which operates with a Chinese name. That gambling facility creates marketing collateral or gets news coverage which uses a different name or a spelling which is different from the operation’s actual name. As a result, missing a news item related to that operation is an on-going problem for some professionals.

Bitext has revealed that its proprietary technology can perform the same tagging and extraction process for organizational names in more than two dozen languages. In “Bitext NAMER Cracks Named Entity Recognition,” the company reports:

… issues arise with organizational names, such as “Sun City” (a place and enterprise) or aliases like “Yati New City” for “Shwe Koko”; and, in general, with any language that is written in non-Roman alphabet and needs transliteration. In fact, these issues affect to all languages that do not use Roman alphabet including Hindi, Malayalam or Vietnamese, since transliteration is not a one-to-one function but a one-to-many and, as a result, it generates ambiguity the hinders the work of analysts. With real-time data streaming into government software, resolving ambiguities in entity identification is crucial, particularly for investigations into activities like money laundering.

Unlike some other approaches — for instance, smart large language models — the Bitext NAMER technology:

  • Identifies correctly generic names
  • Performs type assignment; specifically, person, place, time, and organization
  • Tags AKA (also known as) and pseudonyms
  • Distinguishes simile names linked to unelated entitles; for example, Levo Chan.

The company says:

Our unique method enables accurate, multilingual entity detection and normalization for a variety of applications.

Bitext’s technology is used by three of the top five US companies listed on NASDAQ. The firm’s headquarters are in Madrid, Spain. For more information, contact the company via its Web site, www.bitext.com.

Stephen E Arnold, December 11, 2024

Comments

Got something to say?





  • Archives

  • Recent Posts

  • Meta