1. 1-24 of 6218 1 2 3 4 ... 257 258 259 »
    1. Identifying entity synonyms

      Embodiments for identifying an entity synonym of an entity are described. A query log is stored in a database located on at least one computing device. A candidate generation module can select a candidate query in the query log that shares a click on a URL with the entity. A correlated tag module can generate a set of phrase-tag pairs for the entity and the candidate query and measure a mutual information value for each phrase-tag pair. A candidate filtering module can determine a click similarity value between the candidate query and the entity based on a set of URLs ...

      Read Full Article
    2. Short text messaging in digital mobile telecommunication networks

      A digital mobile telecommunications method using a digital telecommunications system. The method comprises: requesting the message from the content provider by the telecommunications device; receiving the message by the telecommunications device via the digital mobile telecommunications network from a content provider; sending the message to a text classification system by the telecommunications device via the wired digital network and the digital mobile telecommunications network; creating text tokens from the text portion using a tokenizing algorithm by the text classification system; transforming the text tokens into stemmed tokens using a stemming algorithm by the text classification system; determining a word classifier ...

      Read Full Article
    3. Collaborative communication system with real-time anticipatory computing

      Contextual content is provided to a first conversation participant via a client device of the first conversation participant. Communication information associated with a conversation is received via the first client device interface. Context information associated with the conversation is retrieved from the received communication information. One or more concepts associated with the conversation are identified based on the context information. Content is selected for presenting on the client device based on the identified concepts. The selected content is then presented to the first conversation participant in a second client device interface.

      Read Full Article
    4. System and method for predicting impending cyber security events using multi channel behavioral analysis in a distributed computing environment

      Multi channel distributed behavioral analysis architecture provides a software solution to the major operational challenges faced with providing an early warning system for impending cyber security events. Most cyber security events are premeditated. However, many current cyber security defense technologies only address the real-time detection of a software vulnerability, the presence of malware (known or unknown "zero day"), anomalies from pre-established data points, or the signature of an active security event. The system and method of the multi channel distributed behavioral analysis architecture introduces a technique which provides the data collection, assessment, and alerting ability prior to the occurrence of ...

      Read Full Article
    5. System, device and method for processing interlaced multimodal user input

      A device, method and system are provided for interpreting and executing operations based on multimodal input received at a computing device. The multimodal input can include one or more verbal and non-verbal inputs, such as a combination of speech and gesture inputs received substantially concurrently via suitable user interface means provided on the computing device. One or more target objects is identified from the non-verbal input, and text is recognized from the verbal input. An interaction object is generated using the recognized text and identified target objects, and thus comprises a natural language expression with embedded target objects. The interaction ...

      Read Full Article
    6. Electronic message systems and methods

      Methods and systems to process computer readable electronic messages, such as electronic mail messages or e-mail. Methods and system include auto-tagging based on one or more of statistical machine learning based clustering techniques, custom parsers, and crowd-sourced message tagging. Methods and systems further include relevancy determination based on combinations of features, user-configurable hybrid web browser/e-mail client rendering, tabbed rendering, plug-in based local computational features, implied social graph based decision making, and automatic detection of account settings.

      Read Full Article
    7. Markov-based sequence tagging using neural networks

      Features are disclosed for using a neural network to tag sequential input without using an internal representation of the neural network generated when scoring previous positions in the sequence. A predicted or determined label (e.g., the highest scoring or otherwise most probable label) for input at a given position in the sequence can be used when scoring input corresponding to the next position the sequence. Additional features are disclosed for training a neural network for use in tagging sequential input without using an internal representation of the neural network generated when scoring previous positions the sequence.

      Read Full Article
    8. Method and system for evaluating query suggestions quality

      Methods, systems and programming for evaluating query suggestions quality. In one example, a plurality of query suggestions are provided in a ranking to a user. A user activity with respect to one of the plurality of query suggestions is detected. A position of the one of the plurality of query suggestions in the ranking is determined. A quality measure of the plurality of query suggestions is calculated based, at least in part, on the user activity and the position of the one of the plurality of query suggestions.

      Read Full Article
    9. Computer-implemented system and method for generating an interest profile for a user from existing online profiles

      A computer-implemented system and method for generating an interest profile for a user from user generated content on existing online profiles is provided. Interest categories are maintained in a database and each interest category is associated with an initial interest index score. User generated items are selected from an existing online profile and each user generated item is associated with a weight. For each user generated item, similarity mapping is performed with each of the interest categories in the database by extracting artifacts from each user generated item, calculating an artifact similarity score for each of the extracted artifacts, obtaining ...

      Read Full Article
    10. Systems, methods, and software for entity relationship resolution

      To facilitate access to public records, the present inventors devised, among other things, an entity resolution system. The exemplary system includes master records database of 300 million entities, which is partitioned into multiple distinct portions. The exemplary system extracts entity information from input public records and constructs one or more blocking queries against specific portions of the master records database to identify one or more sets of candidate records. Feature vectors are defined for the candidate records and machine learning techniques, such as Support Vector Machine, are used to determine which of the candidate records from the master records database ...

      Read Full Article
    11. Model shrinking for embedded keyword spotting

      A revised support vector machine (SVM) classifier is offered to distinguish between true keywords and false positives based on output from a keyword spotting component of a speech recognition system. The SVM operates on a reduced set of feature dimensions, where the feature dimensions are selected based on their ability to distinguish between true keywords and false positives. Further, support vectors pairs are merged to create a reduced set of re-weighted support vectors. These techniques result in an SVM that may be operated using reduced computing resources, thus improving system performance.

      Read Full Article
      Mentions: SVM
    12. Context-based data storage management between devices and cloud platforms

      A system, method and program product that provides context-based data storage management between a cloud platform and a mobile device. A system is disclosed that includes: a system for assigning context to user files stored in a cloud platform; a system for periodically analyzing schedule information and location information associated with a user to determine a current user context; a system for matching the current user context with user files stored in the cloud platform to identify a set of context matching files; and a system for periodically downloading context matching files from the cloud platform to a mobile device ...

      Read Full Article
    13. Cognitive alert control framework for mobile devices

      A method for providing a cognitive alert control framework for a mobile device, wherein the mobile device includes an alert mechanism is provided. The method may include detecting, by a processor, a call being initiated by a caller using a first mobile device to a recipient using a second mobile device. The method may also include determining a cognitive state of the caller. The method may further include determining a cognitive state of the recipient. The method may include analyzing a relationship between the caller and the recipient based on the determined cognitive state of the caller and the determined ...

      Read Full Article
    14. Cognitive digital security assistant utilizing security statements to control personal data access

      An approach is provided in which a cognitive digital security assistant intercepts a personal data request from a client that is requesting personal data from a user. The cognitive digital security assistant analyzes the personal data request against the user's security statements to determine whether to provide the user's personal data to the client. During the analysis, the cognitive digital security assistant determines whether the personal data request includes benefits that meet the user's benefit thresholds included in the user's security statements. When the benefits meet the user's benefit thresholds, the cognitive digital security assistant ...

      Read Full Article
    15. Computing system with social interaction mechanism and method of operation thereof

      A computing system includes: a control unit configured to: detect an upcoming event for interacting with a focal person for the upcoming event; extract an invitee's identification for the upcoming event, aggregate an invitee's information associated with the invitee's identification; build a social graph as an enhanced graph or with an extension graph based on the invitee's information for adding an invitee associated with the invitee's identification; and a storage unit, coupled to the control unit, configured to store the social graph.

      Read Full Article
    16. Using reading levels in responding to requests

      A request can be received and a request reading level representation for the request can be inferred. In response to the request, the request reading level representation can be compared with one or more reading difficulty level representations for one or more response items. Also in response to the request, one or more indications of results of comparing the request reading level representation with one or more reading difficulty level representations for the one or more response items can be returned. The indication(s) may include a ranking of the response items. The ranking can be based at least in ...

      Read Full Article
    17. Systems and method for searching an index

      Embodiments of the invention form an information set from the current set of index information available by the operations of the pre-search and runtime Search components of the search engine. A search request that contains search terms and/or other search criteria (e.g. date or file type) is entered by a user through an input interface. The search terms and the information set are worked through the search engine modules to provide the actual results sought by the user. These results are provided to the user via an output interface. Embodiments involve converting a search request into a format ...

      Read Full Article
    18. Updating a search index used to facilitate application searches

      Techniques are disclosed for maintaining a search index used to support application searches. The techniques include receiving application data from one or more data sources, identifying an application referenced in the application data. The techniques further include extracting a plurality of attributes corresponding to the application from the application data based on an application specific search schema. The techniques also include generating an application representation of the application based on the plurality of attributes and the application specific search schema. The techniques also include updating a search index with the application representation.

      Read Full Article
    19. Tag management in a tag cloud

      A method for managing tags in a tag cloud may include receiving a tag for an object and comparing the tag to existing tags for the object. The comparing may include determining if there is a relationship between the tag and any of the existing tags. The method may also include adding the tag to the tag cloud in response to there being no relationship between the tag and any of the existing tags. The method may additionally include selecting one tag of the existing tags in response to the tag and the one tag being related tags. The method ...

      Read Full Article
    20. E-services translation utilizing machine translation and translation memory

      A system and method for translating data from a source language to a target language is provided wherein machine generated target translation of a source sentence is compared to a database of human generated target sentences. If a matching human generated target sentence is found, the human generated target sentence may be used instead of the machine generated sentence, since the human generated target sentence is more likely to be a well-formed sentence than the machine generated sentence. The system and method does not rely on a translation memory containing pairs of sentences in both source and target languages, and ...

      Read Full Article
    21. Method and apparatus for aggregating with information generalization

      Methods, apparatuses, and computer program products are described herein that are configured to perform aggregation of phrase specifications. In some example embodiments, a method is provided that comprises identifying two or more generalized phrase specifications. In some example embodiments, the two or more generalized phrase specifications contain at least one aggregatable constituent. The method of this embodiment may also include generating an aggregated phrase specification from the two or more generalized phrase specifications. In some example embodiments, the aggregated phrase specification comprises a combined noun phrase generated from the aggregatable constituents and one or more additional constituents based on a ...

      Read Full Article
    22. Method for detecting grammatical errors, error detection device for same and computer-readable recording medium having method recorded thereon

      An apparatus for detecting grammatical errors includes: a sentence analyzer to break up an input sentence into units of morphemes; an example builder to break up example text into units of morphemes and build an example-based index database (DB); and an error detector to generate morpheme sequences by binding the morphemes broken up from the input sentence in a preset window (n-window) size, the generated morpheme sequences comprising forward morpheme sequences and backward morpheme sequences, determine frequencies of appearance of morpheme sequences identical to the forward morpheme sequences and backward morpheme sequences by searching the example-based index DB, and detect ...

      Read Full Article
    23. Discovering relationships in tabular data

      A system, and computer program product for discovering relationships in tabular data are provided in the illustrative embodiments. A set of documents is received, a document in the set including the tabular data. A cell in the tabular data is selected whose dependencies are to be determined. A hypothesis to use in conjunction with the cell is selected. Whether the hypothesis applies to a selected portion of the document is tested by determining whether a conclusion in the hypothesis can be computed using a function specified in the hypothesis on the selected portion. The selected portion can be a selected ...

      Read Full Article
    24. System and method for speech-based navigation and interaction with a device's visible screen elements using a corresponding view hierarchy

      Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enabling screen-specific user interfacing with elements of viewable screens presented by an electronic device are disclosed. In one aspect, a method includes the actions of identifying a character sequence representing a first input that is received while displaying a viewable screen having at least one selectable viewable element. The actions further include accessing an electronic file that provides a text representation of one or more of the at least one selectable viewable element. The actions further include comparing the character sequence to the text representation. The ...

      Read Full Article
    1-24 of 6218 1 2 3 4 ... 257 258 259 »
  1. Categories

    1. Default:

      Discourse, Entailment, Machine Translation, NER, Parsing, Segmentation, Semantic, Sentiment, Summarization, WSD