Abstract: A method of conversion of imines substituted with —X—R1 into amidines includes reacting a starting material compound including an imine that comprises —X—R1 bound to an imine carbon atom of the imine with a nitrogen-containing reagent to form a product compound including an amidine in place of the imine —X—R1 in the starting material compound. The nitrogen-containing reagent includes a primary amine, a secondary amine, an ammonium salt, or a combination thereof. The variable X is —S—, —O—, or —NH—. The variable R1 is substituted or unsubstituted (C1-C20) hydrocarbyl, wherein R1 is optionally bonded to a solid support. A method of forming a cyclized product includes intramolecularly reacting an amidine with a carbonyl carbon to form the cyclized product including a 4H-imidazolone and/or a derivative thereof.

Abstract: Named entity recognition is described, for example, to detect an instance of a named entity in a web page and classify the named entity as being an organization or other predefined class. In various examples, named entity recognition results are used to augment text from which the named entity was recognized; the augmentation may comprise information retrieval results about the named entity mention. In various embodiments, labeled training sentences in many different languages and for many different classes, are obtained to train machine learning components of a multi-lingual, multi-class, named entity recognition system. In examples, labeled training sentences are obtained from at least two sources, a first source using a multi-lingual or monolingual corpus of inter-linked documents and a second source using machine translation training data. In examples, labeled training sentences from the two sources are selectively sampled for training the named entity recognition system.

Abstract: Named entity recognition is described, for example, to detect an instance of a named entity in a web page and classify the named entity as being an organization or other predefined class. In various examples, named entity recognition results are used to augment text from which the named entity was recognized; the augmentation may comprise information retrieval results about the named entity mention. In various embodiments, labeled training sentences in many different languages and for many different classes, are obtained to train machine learning components of a multi-lingual, multi-class, named entity recognition system. In examples, labeled training sentences are obtained from at least two sources, a first source using a multi-lingual or monolingual corpus of inter-linked documents and a second source using machine translation training data. In examples, labeled training sentences from the two sources are selectively sampled for training the named entity recognition system.