Abstract:
Systems and methods for automatic semantic labeling of natural language documents provided in electronic or digital form include a semantic processor that performs a basic linguistic analysis of text, including recognizing in the text semantic relationships of the type objects and/or classes of objects, facts and cause-effect relationships; matching linguistically analyzed text against target semantic relationship patterns, created by generalization of particular cases of target semantic relationships; and generating semantic relationship labels based on linguistically analyzed text and a result of the matching.
Abstract:
A virtual pet question and answer server, including a natural language understanding module and a response sentence generation module. A virtual pet chat system, including a virtual pet client unit (101), a maintenance virtual pet data unit (102) and a question and answer unit (103). A virtual pet chatting method, the first virtual pet sends a natural language question to the second virtual pet; the second virtual pet is based on the natural language question, after a natural language understanding, combines with the virtual pet's attribute to perform the inference, generates a natural language response sentence.
Abstract:
A method and a system for integrating multimodal interpretations (MMIs) in user inputs to a data processing system (100) are provided. The method includes generating (603) a set of MMIs, based on the user inputs collected during a turn. The set of MMIs includes at least one semantic relationship function, the semantic relationship function denoting a semantic relationship between values determined from the user inputs entered through one or more of the at least one input modality, the semantic relationship function comprising at least one semantic operator. The method further includes generating (604) sets of joint MMIs. Each set of joint MMIs includes MMIs of semantically compatible types. The method further includes resolving (606) the reference values of the references of each set of joint MMIs to generate corresponding sets of reference resolved MMIs. The method further includes generating (608) an integrated MMI for each set of reference-resolved MMIs.
Abstract:
A method for operating a multi-modal dialog system (104) is provided. The multi-modal dialog system (104) comprises a plurality of modality recognizers (202), a dialog manager (206), and a grammar generator (208). The method interprets a current context of a dialog. A template (216) is generated, based on the current context of the dialog and a task model (218). Further, a current modality capability information (214) is obtained. Finally, a multi-modal grammar (220) is generated based on the template (216) and the current modality capability information (214).
Abstract:
A fully web-enabled method for diagrammatically representing the meaningful structure of a complex argument or debate, or other similar information, as a schematic map made up of nodes each of which represent a discrete element in said meaningful structure comprising the steps of: (a) Beginning a new map by specifying the broad subject matter and other data about said map and selecting from one of a plurality of sets of encoded information and rules, termed Map Grammars, that constrain how nodes of different types may be combined to form maps and the actions available to persons building, editing or otherwise interacting with such maps. (b) Associating selected information items relevant to said argument or debate, or other information, with map nodes. (c) Adding nodes to said schematic map in such a way as to form an overall structure in which nodes are organized so as to conform to said Map Grammar at all times.
Abstract:
Arbitrary knowledge and language is retained, manipulated, and transformed according to a universal grammar that defines the mind’s innate action on language, or the “deep” structure and meaning of language, in analogue and digital devices and software according to operations and knowledge network structures, including programmable digital bytes configured into epistemic moments and parse trees made therefrom.
Abstract:
Die Erfindung betrifft ein sprachverarbeitendes System, welches Zumindest einen Extraktor als Einrichtung zur lexikalischen Zuordnung der zu verarbeitenden Sprache und zumindest einen Konnektor als Einrichtung zur Verknüpfung der lexikalisch zugeordneten Sprache zu einer Aussage umfasst. Erfindungsgemäss ordnet der Extraktor der zu verarbeitenden Sprache Begriffe zu (Begriffe sind beispielsweise Objekte, Ereignisse, Eigenschaften (Begriffsklassen), bei denen einer Variable zugehörige Begriffe, Merkmale und/oder komplexere Strukturen zugeordnet sind, so dass durch diese Strukturen, wie Begriffe, Merkmale und/oder komplexere Strukturen der entsprechende Begriff mit Leben gefüllt und somit verstanden werden kann). Im Gegensatz zu den gängigen statistischen Verfahren zur Sprachverarbeitung analysiert das hier beschriebene System nicht Auftretenswahrscheinlichkeit von Klangfolgen (gesprochene Sprache) oder Zeichenketten (geschriebene Sprache), sondern extrahiert und verarbeitet die begriffliche Bedeutung sprachlicher Botschaften. Alle Kernprozeduren und Wissensbasen des Systems operieren daher sprachenunabhängig. Um den Input einer spezifischen Landessprache zu verarbeiten, ist lediglich das jeweilige sprachspezifisches Lexikon hinzuzufügen. Die vorliegende Erfindung ermöglicht die Bedeutungsrekonstruktion auch syntaktisch/grammatikalisch falscher sprachlicher Anweisungen.
Abstract:
Disclosed is an automated system and machine-readable code for generating descriptive multi-word groups from a digitally encoded, natural-language input text that describes a concept, invention, or event in a selected field. The system includes an electronic digital computer (22), a word-group database (32, 34) accessible by said computer (22), and a computer readable code of the type just described. The word-group database (32, 34) provides, or can be used to calculate, the selectivity value of each of a plurality of word groups (40) representing proximately arranged non-generic words derived from a plurality of digitally encoded natural language texts in the selected field and in one or more unrelated fields.
Abstract:
A system through which verbal information can be utilized to create structured data with tags (2) or inserted codes such as XML code or the like provides hand held capability for easy adoption. A visual display (13) at the time of dictation can provide checklists, prompts or otherwise shape the entry to comport to a selected data context. The visual display can also ba part of a transcriptionist system (7). By providing data in a coded fashion, analysis can be easily conducted such that alerts, bioterror alerts (e.g. evolving symptom or trend information for anthrax or the like) can be rapidly and perhaps automatically identified, and acted upon such as in providing health care alerts or locationally oriented statistical analysis information. A central database (1) reporting function to a central authority (11) (e.g., to the CDC or law enforcement) can be included for terrorist and other event management.
Abstract:
An ontology-based parser incorporates both a system and method for converting natural-language text into predicate-argument format that can be easily used by a variety of applications, including search engines, summarization applications, categorization applications, and word processors. The ontology-based parser contains functional components for receiving documents in a plurality of formats, tokenizing them into instances of concepts from an ontology, and assembling the resulting concepts into predicates. The ontological parser has two major functional elements, a sentence lexer and a parser. The sentence lexer takes a sentence and converts it into a sequence of ontological entities that are tagged with part-of-speech information. The parser converts the sequence of ontological entities into predicate structures using a two-stage process that analyzes the grammatical structure of the sentence, and then applies rules to it that bind arguments into predicates.