Iconic Translation Machines (Iconic), a leading Machine Translation (MT) software and solutions provider is pleased to announce its involvement in the creation of ChemZent™, the first and only indexed and searchable English-language version of Chemisches Zentralblatt – the oldest compendium of German chemistry abstracts dating from 1830-1969.
Iconic partnered with CAS, a division of the American Chemical Society, to produce ChemZent. This new CAS solution provides immeasurable value to researchers and institutions worldwide by allowing users to access the entire Chemisches Zentralblatt collection in one place using SciFinder ®, searchable in English with indexing of relevant chemical substances and concepts for ease of discoverability.
Iconic enabled this solution by developing innovative machine learning technology to extend its existing machine translation and natural language processing solutions. Iconic’s unrivalled expertise together with CAS industry-leading scientific information analysis made the launch of ChemZent possible within one year of idea inception.
The process of creating ChemZent involved large scale digitisation and translation of 140 years’ worth of German chemical information – journals and patents – for indexing and search. Iconic digitised 800,000 image-based PDF documents via Optical Character Recognition (OCR).
It then extracted individual articles, separated them into fields by author and title, and machine translated them from German into English, before CAS indexed the records for search. On completion more than 3 million chemical abstracts and one billion words were translated across the entire Chemisches Zentralblatt collection.
Full case study available here: www.iconictranslation.com/cas-chemzent/