Embodiments include method, systems and computer program products for narrative generation using pattern recognition by topic. In some embodiments, a topic may include identified from content. Events associated with the topic may be obtained from one or more sources. The events may be processed. A narrative of the topic may be generated using pattern recognition on the events. The narrative may be transmitted for presentation to a user.

A gesture based system for translation and transliteration of input text, and a corresponding method have been disclosed. The system and method provide for selective translation and transliteration of the input text, based on the gestures performed by a user. When the user performs a left swipe gesture, input text which is in a first language is translated into a language prescribed by the user. In the event that the user performs a right-swipe, the input text is transliterated from a first language, into a language prescribed by the user. The user is also enabled to switch back to the original language of the input text, that is, the first language, by performing predetermined gestures.

A plurality of annotations can be received for a presentation presented in a web conference. For each of the plurality of annotations, a respective portion of the presentation to which the annotation pertains can be determined, and a respective relevance parameter can be assigned to the annotation. The relevance parameter can indicate a relevance of the annotation to the respective portion of the presentation to which the annotation pertains. For each of the plurality of annotations, the annotation can be assigned to a respective location of a view based on the relevance parameter assigned to the annotation and the annotation can be presented in the respective location of the view to which the annotation is assigned.

Provided is a mobile terminal including: a display unit on which screen information is output; a translation function unit that translates a translation-source information portion of the screen information that is output to the display unit; and a controller that outputs translation-target information into which the translation-source information portion is translated using the translation function unit, on a translation window, in which in a state where the screen information is output on the display unit, the translation window is positioned in one region of the display unit.

A system and method for adapting a speech recognition and generation system. The system and method include providing a speech recognition and generation engine that processes speech received from a user and providing a dictionary adaptation module that adds out of vocabulary words to a baseline dictionary of the speech recognition and generation system. Words are added by extracting words that are encountered and adding out of vocabulary words to the baseline dictionary of the speech recognition and generation system.

In an example embodiment, a memory stores a database of text objects having textual information pertaining to at least one of a plurality of documents, and contextual information about the documents. A translation module then is configured to translate text from a first user from a first language to a second language, the text pertaining to a first of the plurality of documents. A context ranking module is configured to locate, in the database, a plurality of text objects, in the second language, having text similar to the translated text, and to rank the plurality of text objects having text similar to the translated text based on a comparison of contextual information about the first document and the contextual information stored in the database for documents corresponding to the plurality of text objects having text similar to the translated text.

In order to solve a conventional problem that an accurate translation cannot be realized, a learning apparatus includes: a parser unit parsing a target language sentence, thereby acquiring a binary tree of the target language sentence; a source language element acquiring unit acquiring one or more source language elements; a source language partial structure acquiring unit acquiring one or more source language partial structures each containing a parent node having a phrase label and two child nodes each having a phrase label or a source language element; a labeling unit providing a reordering label to the one or more source language partial structures; a model building unit that builds one or more parsing models each having appearance probability information regarding a labeled source language partial structure; and an accumulating unit accumulating a binary tree of a source language sentence having the one or more parsing models.

A computer-implemented method can include obtaining (i) an aligned bi-text for a source language and a target language, and (ii) a supervised sequence model for the source language. The method can include labeling a source side of the aligned bi-text using the supervised sequence model and projecting labels from the labeled source side to a target side of the aligned bi-text to obtain a labeled target side of the aligned bi-text. The method can include filtering the labeled target side based on a task of a natural language processing (NLP) system configured to utilize a sequence model for the target language to obtain a filtered target side of the aligned bi-text. The method can also include training the sequence model for the target language using posterior regularization with soft constraints on the filtered target side to obtain a trained sequence model for the target language.

Systems and methods for converting a natural language sentence into a computer-readable primitive sentence and extracting information therefrom are disclosed. A method includes identifying, by a processing device, a verbal block in the natural language sentence, splitting, by the processing device, the natural language sentence into one or more logical clauses, determining, by the processing device, a type for each logical clause, where the type indicates whether each logical clause contains an ambiguous verbal block, disambiguating, by the processing device, the ambiguous verbal block within each logical clause, where each verbal block is considered independently of a noun phrase, and constructing, by the processing device, the computer-readable primitive sentence for each ambiguous verbal block by duplicating a shared noun phrase of the ambiguous verbal block. The computer-readable primitive sentence improves functioning of a computing device by allowing the computing device to process the natural language sentence to obtain information therefrom.

An interactive electronic translation and communications process is provided for use in a translation station that provides a mobile or stationary fixed interactive facility for interviews or interrogations to be carried out between two persons speaking in different languages. The process can be assisted by animated virtual characters (avatars) realistically created and displayed on a computer screen to represent ethnic looks from around the globe. The avatars can be lip synchronized to deliver messages to the interviewee in the interviewee's languages and can guide the users and interviewee through a series of questions and answers. Biometric conditions of the interviewee and electronic identification of the interviewee can also be readily accomplished by the novel process. The process is particularly useful for hospitals, law enforcement, military, airport security, transportation terminals, financial institutions, and government agencies.