Abbyy Production LLC

Abbyy Infopoisk LLC

Anton Krivenko

Konstantin Zuev

Konstantin Anisimovich

Vladimir Pavlovich Selegey

Tatiana Parfentieva

Sergey Gaydaenko

Disclosed are systems, computer-readable mediums, and methods for representing text. A document that includes text is received in a first format. A universal text representation of the document is created using a first filter associated with the first format. The universal text representation presents the text and supported non-text data and preserves unsupported data with binding to supported data. The universal text representation is modified based upon input from a user using a program in a what you see is what you get (WYSIWYG) mode. The user can see a location of where the supported data and unsupported data are kept. The modified universal text representation is exported using a second filter associated with a second format. The supported and unsupported non-text data are exported.

Universal text representation with import/export support for various document formats

Computer-implemented systems and methods align fragments of a first text with corresponding fragments of a second text, which is a translation of the first text. One preferred embodiment preliminarily divides the first and second texts into fragments; generates a hypothesis about the correspondence between the fragments of the first and second texts; performs a lexico-morphological analysis of the fragments using linguistic descriptions; performs a syntactic analysis of the fragments using linguistic descriptions and generates syntactic structures for the fragments; generates semantic structures for the fragments; and estimates the degree of correspondence between the semantic structures.

Methods and systems for alignment of parallel text corpora

Growing community of inventors

Moscow, Russia

Anton Krivenko