Patent application number | Description | Published |
20080319749 | GENERIC SPELLING MNEMONICS - A system and method for creating a mnemonics Language Model for use with a speech recognition software application, wherein the method includes generating an n-gram Language Model containing a predefined large body of characters, wherein the n-gram Language Model includes at least one character from the predefined large body of characters, constructing a new Language Model (LM) token for each of the at least one character, extracting pronunciations for each of the at least one character responsive to a predefined pronunciation dictionary to obtain a character pronunciation representation, creating at least one alternative pronunciation for each of the at least one character responsive to the character pronunciation representation to create an alternative pronunciation dictionary and compiling the n-gram Language Model for use with the speech recognition software application, wherein compiling the Language Model is responsive to the new Language Model token and the alternative pronunciation dictionary. | 12-25-2008 |
20090006332 | FEDERATED SEARCH - Various techniques are disclosed to permit searching several locations with one query. Locations may include web search sites, subscription-only sites, line of business applications, or other searchable data repositories. The query may be modified to provide the required format or other information for each location to perform a search. | 01-01-2009 |
20090187550 | SPECIFYING RELEVANCE RANKING PREFERENCES UTILIZING SEARCH SCOPES - A mechanism for expressing a user preference to a set of documents based on user knowledge about the document corpora. The user preference input to the system can be positive, negative, or both. A set of documents that can be identified with a query can define a search scope definition. The search scope is mapped into an input ranking feature for a ranking function. The search scope definition is employed as a soft preference ranking feature, and thus, used to bias ranking via relevance feedback. The mechanism facilitates increasing or decreasing the final ranking score of a document based on whether the document falls into the user scope. The ranking weight can be configured by the user ad-hoc, or when relevance judgments are available, using machine learning techniques to find the optimal weights to optimize ranking. | 07-23-2009 |
20090198667 | Generating Search Result Summaries - Embodiments are configured to provide a summary of information associated with one or more search results. In an embodiment, a system includes a summary generator that can be configured to provide a summary of information including one or more snippets associated with a search term or search terms. The system includes a ranking component that can be used to rank snippets and the ranked snippets can be used when generating a summary that includes one or more ranked snippets. In one embodiment, the system can be configured to include one or more filters that can be used to filter snippets and the filtered snippets can be used when generating a summary. Other embodiments are available. | 08-06-2009 |
20090319266 | MULTIMODAL INPUT USING SCRATCHPAD GRAPHICAL USER INTERFACE TO EDIT SPEECH TEXT INPUT WITH KEYBOARD INPUT - A system and method for multimodal input into an application program. The method may include performing speech recognition on speech audio input to thereby produce recognized speech text input for insertion into a document of an application program, the document having keyboard focus. The method may also include identifying the document as being text service framework unaware. The method may further include displaying the recognized speech text input in a scratchpad graphical user interface for editing the recognized speech text input. The method may further include reflecting keyboard input bound for the document to the scratchpad graphical user interface, while preserving the keyboard focus of the document. The method may also include displaying the reflected keyboard input on the scratchpad graphical user interface, to thereby effect edits in the recognized speech text input. | 12-24-2009 |
20090319505 | TECHNIQUES FOR EXTRACTING AUTHORSHIP DATES OF DOCUMENTS - Various technologies and techniques are disclosed for calculating authorship dates for a document. A portion of a document to select to look for possible authorship dates is determined. The possible authorship dates are extracted from the portion of the document. A revised authorship date of the document is generated using a neural network. The revised authorship date is returned to an application or process that requested the date. | 12-24-2009 |
20090319521 | NAME SEARCH USING A RANKING FUNCTION - An approach is described for performing a name search using a name search operation and a ranking operation. The name search operation may take text as input and apply a fuzzy matching operation and a lookup operation to generate a collection of candidate names with respective probability scores. In other cases, speech or handwriting recognition may generate the collection of candidate names and probability scores. The ranking operation may then rank these candidate names using a ranking function. The ranking function may rank the candidate names based on the probability scores associated with the names and at least one other factor. One such factor may reflect whether information provided by a user matches profile information associated with a candidate name under consideration. Another factor may reflect an extent of a nexus between the user and a person associated with the candidate name. Other types of factors can be used. | 12-24-2009 |
20100265257 | CHARACTER MANIPULATION - Embodiments for manipulating characters displayed on a display screen are provided, wherein one example method includes identifying a selected word, wherein the selected word includes at least one character to be modified. The method further includes correlating each of the at least one character with a unique numerical value and receiving a selection command and a modification command, wherein the selection command is the unique numerical value corresponding to a selected character. Furthermore, the method includes modifying the selected character responsive to the modification command to generate a modified word. | 10-21-2010 |
20110066611 | GENERATING SEARCH RESULT SUMMARIES - Embodiments are configured to provide a summary of information associated with one or more search results. In an embodiment, a system includes a summary generator that can be configured to provide a summary of information including one or more snippets associated with a search term or search terms. The system includes a ranking component that can be used to rank snippets and the ranked snippets can be used when generating a summary that includes one or more ranked snippets. In one embodiment, the system can be configured to include one or more filters that can be used to filter snippets and the filtered snippets can be used when generating a summary. Other embodiments are available. | 03-17-2011 |
20110313992 | Generating Search Result Summaries - Embodiments are configured to provide a summary of information associated with one or more search results. In an embodiment, a system includes a summary generator that can be configured to provide a summary of information including one or more snippets associated with a search term or search terms. The system includes a ranking component that can be used to rank snippets and the ranked snippets can be used when generating a summary that includes one or more ranked snippets. In one embodiment, the system can be configured to include one or more filters that can be used to filter snippets and the filtered snippets can be used when generating a summary. Other embodiments are available. | 12-22-2011 |
20140222792 | NAME SEARCH USING A RANKING FUNCTION - An approach is described for performing a name search using a name search operation and a ranking operation. The name search operation may take text as input and apply a fuzzy matching operation and a lookup operation to generate a collection of candidate names with respective probability scores. In other cases, speech or handwriting recognition may generate the collection of candidate names and probability scores. The ranking operation may then rank these candidate names using a ranking function. The ranking function may rank the candidate names based on the probability scores associated with the names and at least one other factor. One such factor may reflect whether information provided by a user matches profile information associated with a candidate name under consideration. Another factor may reflect an extent of a nexus between the user and a person associated with the candidate name. Other types of factors can be used. | 08-07-2014 |