Abstract: An apparatus and a concomitant method for natural language understanding. In one embodiment, the present invention provides a new architecture that employs a sophisticated natural language understanding parser in conjunction with a speech recognition component and a VoiceXML application.

Abstract: An apparatus and a concomitant method for speech recognition. In one embodiment, a distributed speech recognition system provides speech-driven control and remote service access. The distributed speech recognition system comprises a client device and a central server.

Abstract: Systems and methods for processing automatically generated recommendations. In various exemplary embodiments, a method of producing a recommendation digest for a user includes (a) generating a recommendation log for the user by storing a plurality of recommendations, one or more of the plurality of recommendations relating to a representation of a context that led to the creation of the one or more recommendations for the user, and (b) determining a subset of recommendations by using one or more statistics obtained from processing the plurality of recommendations stored in the log.

Abstract: A medium, system and method of processing content information. In one exemplary embodiment, the medium, system and method include determining associated previously accessed content information in response to an action performed on a document containing information and based on a context of the information, and indicating to a user the determined associated content information.

Abstract: A medium, system and method of generating an information digest document. In various exemplary embodiments, the medium, system and/or method may include determining associated previously accessed content information in response to a user-defined digest specification, and generating a digest document of the associated previously accessed content information.

Abstract: Techniques are provided for segmenting text into categorized discourse constituents and attaching discourse constituents into a structural representation of discourse. Techniques for determining hybrid structural and non-structural summaries of a text are also provided. A text is segmented based on a theory of discourse analysis into at least a main discourse constituent containing spatio-temporal information about a single event in a possible world view. The discourse constituents are then inserted into a structural representation of discourse. Non-structural techniques are used to determine relevance scores and important discourse constituents are determined. Relevance scores are percolated through the structural representation of discourse to determine supporting preceding discourse constituents that preserve grammaticality. A hybrid text summary is then determined based on the structural representation of the discourse and relevance scores.

Abstract: An apparatus and a concomitant method for natural language understanding. In one embodiment, the present invention provides a new architecture that employs a sophisticated natural language understanding parser in conjunction with a speech recognition component and a VoiceXML application.

Abstract: An apparatus and a concomitant method for speech recognition. In one embodiment, a distributed speech recognition system provides speech-driven control and remote service access. The distributed speech recognition system comprises a client device and a central server.