Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer frequently asked questions.

Abstract: A method of prioritizing the automated translation of communications includes capturing and inputting into a data processing system a translation-candidate communication rendered in a first human language. A first data set representative of the translation-candidate communication is stored in computer memory and parsed into communication sub-portions. Communication sub-portions are algorithmically selected for translation depending on their relatedness to a predetermined topic as determined by first-language extraction rules. Each selected communication sub-portion is translated to a translated-data-set sub-portion representative of that selected communication sub-portion in the second human language. Translated-data-set sub-portions are subjected to a secondary filtration process in accordance with which their relatedness to the predetermined topic is determined by second-language extraction rules.

Abstract: A system, method, and computer program for generating and exploiting an approximate language model are provided. The method comprises generating a language model according to an approximate hashing technique. The language model comprises a plurality of event sequences in a target language, and each member of the plurality of the event sequences is associated with at least one count. The language model is queried for a member of the plurality of event sequences. A probability associated with the member of the plurality of event sequences is determined based on results of the query.

Abstract: A system, method, and computer program product for determining the emotional content of an electronic correspondence to route or prioritize the information, to set the expectations of a customer support worker, to flag those workers who are using inappropriate language with the customer, or to determine another best course to send the correspondence. In a preferred embodiment, a customer sends an electronic correspondence to a company via email. Emotionally charged words or symbols in each sentence are detected. The message is then given an emotional ranking which is used to determine what future action is most appropriate for the correspondence.

Abstract: An input handler may receive natural language input associated with a command from a user through a user interface, and a language parser may parse the natural language input to determine parsed natural language input. A context monitor may receive context information associated with the user, and a context parser may parse the context information to obtain parsed context information associated with the natural language input and with the command. A command interpreter may interpret the parsed natural language input, using the parsed context information, to thereby determine the command.

Abstract: A method for enabling input into a handheld electronic device having at least three selectable languages available thereon includes detecting a predetermined input a number of times and switching a selected language between one of the three selectable languages and another of the three selectable languages wherein the another language is an immediately preceding selected language.

Abstract: A method (300 or 400) of key press prediction on a touch-based device or an apparatus (501) can entail registering (302, 402) a position of a touch press attempt on an icon among a plurality of icons presented on the touch-base device, calculating (304, 404) a distance from a center of the icon, calculating (306, 406) a psychomotor probability for each icon in the plurality of icons, calculating (312, 408) a linguistic probability for each icon in the plurality of icons, calculating (314, 410) a predictive index for each icon in the plurality of icons based on the psychomotor probability and the linguistic probability, and registering (310,416) as a user selected icon, an icon with one among a highest predictive index (316, 412) or a probability higher than a predetermined absolute value (308).

Abstract: Methods, and systems, including computer programs encoded on computer-readable storage mediums, including a method for performing semantic interpretation using gaze order. The method includes obtaining data identifying a sequence of gaze attention dwell positions, obtaining a semantic description of elements displayed on a visual display, obtaining a transcription of an utterance, correlating the gaze attention dwell positions with the semantic description of elements to generate a sequence of one or more of the elements, performing semantic interpretation of at least one term included in the transcription based at least on the sequence of the elements, and outputting a result of performing the semantic interpretation of the at least one term.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating suffix rewriting rules. A method includes obtaining a plurality of canonical suffix-rewriting rules each associated with one or more words, generating a suffix tree from the words, selecting a minimum colored subset of the nodes and leaves in the suffix tree, and generating a plurality of final suffix-rewriting rules from the nodes in the minimum colored subset. Another method includes receiving applicable and non-applicable words for a suffix-rewriting rule, generating a suffix tree from the applicable words and the non-applicable words, selecting a minimum colored subset of the nodes and leaves in the suffix tree, and generating a plurality of suffix-rewriting rules, wherein each rule corresponds to a node in the minimum colored subset with a valid status.

Abstract: A software language including language constructs for disambiguating text that is to be converted to speech using configurable lexeme based rules. The language can include at least one conditional statement and a significance indicator. The conditional statement can define a sense of usage for a lexeme. The significance indicator can define a criteria for selecting an associated sense of usage. The language can also include an action expression that is associated with a conditional statement that defines a set of programmatic actions to be executed upon a selection of the associated usage sense. The conditional statement can include a context range specification that defines a scope of an input string for examination when evaluating the conditional statement. Further, the conditional statement can include a directive that represents a defined condition of the lexeme or the text surrounding the lexeme.

Abstract: According to one embodiment, a document proofing support apparatus includes an input unit, an analysis unit, a detection unit, a database unit, a retrieval unit, and a display unit. The input unit is configured to receive input of one of at least one proof document and at least one entry document. The analysis unit is configured to perform a morphological, a syntactic and a dependency analysis and generate analysis information including a dependency relation. The detection unit is configured to detect as a possible coined word character string a compound word having a nominal continuation relation. The database unit is configured to store syntactic information. The retrieval unit is configured to retrieve a dependency-relation sentence, and to determine the possible coined word character string as a coined word if the dependency-relation sentence exists. The display unit is configured to display a message including the coined word.

Abstract: A system offers potential completions for fragments of text. The system may obtain a text fragment and identify documents that include the text fragment. The system may locate sentences within the documents that include at least a portion of the text fragment, identify sentence endings associated with the located sentences, and present the sentence endings as potential completions for the text fragment.

Abstract: Systems and techniques for providing definitions to a user. The provision embodies the context of a text in which the defined term appears. In one aspect, a system includes an electronic device that includes one or more data processing devices programmed to respond to receipt of the user selection of the first term by performing operations. The operations include accessing, from the one or more persistent data storage devices, the characterizations of the contexts of the texts, comparing the accessed characterizations of the contexts of the texts with one or more characteristics of the context of the textual content of a media file, and ranking the definitions of the first term according to respective likelihoods that the definitions appropriately characterize the usage of the first term within the textual content of the media file.

Abstract: The display language of a site may be changed to another alternate language by users of a site at any time. For example, a first user may access the same site in its default language (i.e. English) and a second user may access the site using their preferred language (i.e. French) even though the default language of the site is different from their preferred language. The language of the site may be changed from one language to another language at any time a user is accessing the site. Application content changes are identified by the site helping to ensure consistency between the default language and the alternate languages.

Abstract: An improved method of transliterating non-Latin input within an e-mail address field to the Latin equivalent. A routine in a handheld device is structured to detect a triggering event that indicates an e-mail address is being input into an e-mail address field. Following the triggering event, both prior and subsequent input is transliterated to Latin characters as these characters are required by Internet protocols. The transliteration routine may also be utilized to search an e-mail address book wherein names are recorded using both Latin and non-Latin characters.

Abstract: A method, device and computer program product for parsing linguistic input data by a computer system, in accordance with a grammar of a Formalized Natural Language. The grammar of the Formalized Natural language is a text grammar representing an infinite set of texts of type Text and is stored in electronic form in a computer readable medium constituting a text grammar device. This text grammar is defined by a set of four elements W, N, R and Text. W is a finite set of invariable words of type Word, to be used as terminal, elementary expressions of a text. N is a finite set of non-terminal help symbols, to be used for the derivation and the representation of texts. R is a finite set of inductive rules for the production of grammatical expressions of the Formalized Natural Language, and Text is an element of N and start-symbol for grammatical derivation of all texts of type Text of the Formalized Natural Language.

Abstract: A handheld electronic device includes a reduced QWERTY keyboard and is enabled with disambiguation software that is operable to disambiguate compound text input. The device is able to assemble language objects in the memory to generate compound language solutions. The device is able to analyze the combinations of language objects in light of N-gram data stored on the device to avoid proposing low-probability compound language solutions.

Abstract: An integrated language model includes an upper-level language model component and a lower-level language model component, with the upper-level language model component including a non-terminal and the lower-level language model component being applied to the non-terminal. The upper-level and lower-level language model components can be of the same or different language model formats, including finite state grammar (FSG) and statistical language model (SLM) formats. Systems and methods for making integrated language models allow designation of language model formats for the upper-level and lower-level components and identification of non-terminals. Automatic non-terminal replacement and retention criteria can be used to facilitate the generation of one or both language model components, which can include the modification of existing language models.

Abstract: A handheld electronic device includes a reduced QWERTY keyboard and is enabled with disambiguation software that is operable to disambiguate compound text input. The device is able to assemble language objects in the memory to generate compound language solutions. The device is able to prioritize compound language solutions according to various criteria.

Abstract: A method for determining a sentiment associated with an entity includes inputting a plurality of texts associated with the entity, labeling seed words in the plurality of texts as positive or negative, determining a score estimate for the plurality of words based on the labeling, re-enumerating paths of the plurality of words and determining a number of sentiment alternations, determining a final score for the plurality of words using only paths whose number of alternations is within a threshold, converting the final scores to corresponding z-scores for each of the plurality of words, and outputting the sentiment associated with the entity.