Abstract: The object of the present invention is to enable an apparatus to perform a status analysis indicated by sensor data of a device, etc. based on an expression in a natural language, and to enable an apparatus to operate a device, etc. by an instruction based on a natural language, using a data process technology for handling data with a word. Data groups, which are obtained by directly classifying the input from sensor 1 or obtained after processing this input, are stored in a database 6, in which a word is attached to each of the data groups. On receiving a sensor input, a characteristic is extracted from the sensor input by a characteristic extractor unit 2, and then the sensor input is classified by a characteristic comparison/classification unit 3 using the database 6. If the sensor input does not belong to any of the data groups in the database 6, the sensor input is temporarily stored in a database 7 with no word.

Abstract: A computer search involves expanding a user query with two synonym dictionaries—actions and object—and then validating the expanded queries by comparison with entries in a Subject-Action-Object Knowledge Database (SAO KB) in a discipline corresponding to the query. The latter is prepared from natural language texts and contains fields with subjects, actions, objects, and “main parts of objects” extracted from the object.

Abstract: In response to a user activating a language switching mechanism to indicate a newly selected language, a language switch component sends a language key that corresponds to a first language sensitive element displayed in the user interface to a language resource manager. The language resource manager retrieves from a language resource bundle, which corresponds to the newly selected language, a second language sensitive element. The language switch component then replaces the first language sensitive element with the second language sensitive element. The replacement process is then repeated for all language sensitive elements in the user interface.

Abstract: A method of generating language model statistics for a new word added to a language model incorporating at least one class file containing contextually related words. The method can include the following steps: First, language model statistics can be computed based on references to at least one incorporated class file. Second, a new word can be substituted for each reference to a selected class file. Additionally, the language model statistics can be re-computed based on the new word having been substituted for the reference. Third, the re-computed language model statistics can be displayed in a user interface and modifications can be accepted to the re-computed language model statistics through the user interface. Fourth, the language model statistics can be further re-computed based on the modifications. In consequence, the language model statistics are re-computed for the new word without introducing contextual inaccuracies in the language model.

Abstract: A technique for compressing texts such that referential integrity, sentence coherency, punctuation and readability are preserved and which provides for compression of sentence constituents based on the type of content, the informativity of the sentence constituent and the grammatical readability of the resultant sentence or phrase. Information content portions are parsed to generate parts of speech tags. The informativity of the constituents in a phrase or sentence is determined and the parts of speech having lower information content and having a low effect on grammatical readability of the phrase or sentence are selectively compressed. Parts of speech having successively higher informativity and low effect on grammatical readability are selected for compression until the desired level of compression is reached. Compressed portions are indicated in the summary with a selectable placeholder which expands to display the compressed text.

Abstract: Presented is a system and method for converting or translating expressions in a natural language such as English into machine executable expressions in a formal language. This translation enables a transformation from the syntactic structures of a natural language into effective algebraic forms for further exact processing. The invention utilizes algorithms employing a reduction of sequences of terms defined over an extensible lexicon into formal syntactic and semantic structures. This term reduction incorporates both syntactic type and semantic context to achieve an effective formal representation and interpretation of the meaning conveyed by any natural language expression.

Abstract: A bi-lingual conversion system and method which automatically converts an unrecognizable character stream of one language into another language based on the respective list rule and the pronunciation rule. The bi-lingual conversion method includes storing an incoming character stream in a memory; determining whether the character stream agrees with a respective list rule when a space command is detected in the character stream, and an automatic conversion mode is selected; and converting the character stream into a corresponding character stream of a complementary language according to a pronunciation rule of the respective language when the character stream does not agree with the list rule for providing a faster and more accurate language conversion.

Abstract: A method for morphological disambiguation includes receiving an input string and morphologically analyzing the string to generate a list of candidate analyses of the string, each candidate analysis including a respective word and a linguistic pattern of the word. The pattern of each of the analyses is evaluated against a predefined criterion in order to select one or more of the analyses from the list. The method is suitable particularly for computerized analysis and searching in Hebrew and other Semitic languages.

Abstract: A method and apparatus are provided for adapting a language model to a task-specific domain. Under the method and apparatus, the relative frequency of n-grams in a small training set (i.e. task-specific training data set) and the relative frequency of n-grams in a large training set (i.e. out-of-domain training data set) are used to weight a distribution count of n-grams in the large training set. The weighted distributions are then used to form a modified language model by identifying probabilities for n-grams from the weighted distributions.

Abstract: The sharing of language models is disclosed. In one embodiment, a language model service is provided that is shareable among handlers for input devices. The service includes a pre-processing mode of operation, and a correction mode of operation. In the former mode, the language model service is designed to receive a range within a document from a handler for an input device, and in response provide advice regarding text under consideration by the handler to insert within the document at the range, based on the context of the document within the range. In the latter mode, the language model service is designed to supervise correction over a range of text within a document, in which a number of different handlers for a number of different input devices were initially responsible for insertion of the text, such that the service solicits suggestions from the handlers, and based thereon determines text corrections. The corrections can then be made by the handlers, or by the service.

Abstract: A method and apparatus create a dynamic grammar pertaining to a current user from a global database of data items. A user first identifies himself to the system using a predetermined input identifier, such as an account number, for example. On the basis of this input identifier, the system of the present invention extracts from a global customer database those data items that are associated with the input identifier of the customer. A dynamic grammar including these extracted data items is created, and the system performs a search for a particular data item within this dynamic grammar on the basis of further search criteria that are provided by the customer.

Abstract: In a computer, a user interface allows users to input requests to various applications or software modules executing on the computer. During the input process, the invention presents to the user a grammar-based automatic completion of the user input so far, and/or a grammar-based suggestion list of one or more possible options for completing the user input.

Abstract: Initially, a client requests a specific document and provides the preferences, including readability level preferences of the document, locale preferences, content filtering instructions preferences, governmental regulations preferences, natural language preferences, and document syntactic format preferences. The transcoding proxy requests and receives the document from the origin server, with the document having origin semantic characteristics. The document from the origin server has an origin readability level and origin locale, is conformant with origin content filtering instructions and origin governmental regulations, and is in origin natural language and in origin document syntactic format. Using the client semantics preferences, the transcoding proxy revises the document in a sequential or parallel fashion. The origin semantics characteristics of the document are, thus, revised to the semantic preferences specified by the client.

Abstract: A mechanism is provided for chaining machine translation engines using linguistic annotation language in the intermediate language. A first machine translation engine is provided that translates the source language text into an intermediate language text marked up with linguistic annotation language. A second machine translation engine translates the intermediate language text into the target language using the linguistic annotation language.

Abstract: A method and apparatus are described for automatic processing of electronic communications in a networked computer environment. The invention facilitates the appropriate form of translation of the communication to suit the circumstance. The communication is identified as a foreign language communication, a quotation program is optionally applied to calculate the cost of a human translation and a machine translation program is optionally applied to the foreign language communication. The communication, optional quotation and optional machine translation are forwarded to a recipient. The method is transparent to the sender and receiver.

Abstract: An apparatus and method is disclosed for converting an input signal having frequency related information sustained over a first duration of time into an output signal sustained over a second duration of time at substantially the same first frequency by adding or subtracting to the effective wave length of the output signal. Preferably, the signals are converted in digital form with samples added or subtracted to frequency convert the signal.

Abstract: Embodiments of the present invention provide a method and apparatus for segmenting text by providing orthographic and inflectional variations to a syntactic parser. Under the present invention, possible segments are first identified in the sequence of characters. At least two of the identified segments overlap each other. For at least one of the segments, an alternative sequence of characters is identified. In some cases, this alternative sequence is formed through inflectional morphology, which identifies a different lexical form for a word identified by the segment. In some cases, the alternative sequence represents an orthographic variant of a word identified by the segment. The identified segments and the alternative segments are then passed to a syntactic analyzer, which produces one or more syntactic parses. The segments found in the resulting parses represent the segmentation of the input sequence of characters.

Abstract: A method and apparatus for deriving information from a textual representation of a sentence are provided, the sentence having a plurality of words. The apparatus comprises an input, a processing unit and an output. The input is for receiving data elements indicative of the textual representation of the sentence. The processing unit is operative for processing the textual representation of the sentence to derive an information record on the basis of a set of information extraction rules, the information record being indicative of a semantic representation of at least part of the sentence. The information record is then released at the output. A computer readable medium comprising a program element suitable for execution by a computing apparatus for deriving information from a textual representation of a sentence is also provided.

Abstract: A method of providing a graphical user interface (GUI) in a poetry generation system including displaying a work space, receiving a user input to the word space and linking the user input to a plurality of poet assistant windows. The computer-implemented method of claim 1 wherein The work space may be derived from executing a word processing program. The user input may be a word. The poet assistant's windows may include a combination of a next word window, a finish line window, a finish poem window, a rhyme word window and an alliterative window. Each of the poet's assistant windows may include a poet personality.

Abstract: Systems and methods are provided for generating a language component vocabulary VC for a speech recognition system having a language vocabulary V of a plurality of word forms. One method for generating a language component vocabulary VC for a speech recognition system having a language vocabulary V of a plurality of word forms includes partitioning the language vocabulary V into subsets of word forms based on frequencies of occurrence of the respective word forms, in at least one the subsets, splitting word forms having frequencies less than a threshold to thereby generate word form components and generating a language component vocabulary VC including word forms and word form components. The resulting language component vocabulary, which includes word forms and word components, is used to generate a language model that can be efficiently implemented for real-time automatic speech recognition applications for languages with large vocabularies.