Abstract: A computerized method for implementing a neural architecture for hierarchical sequence labelling comprising: providing a neural architecture comprising a set of labelling layers, wherein the neural architecture uses a multi-pass approach on the set of labelling layers, receiving an input sentence; parsing the input sentence; embedding the input sentence into a corresponding character vector and a corresponding word vector to generate a feature vector; passing the feature vector through the neural architecture; and performing a multi-layer labelling procedure on the feature vector with the neural architecture comprising: augmenting a set of corresponding bits of the feature vector, wherein the feature vector is passed through the set of labelling layers of neural architecture.

Abstract: A computerized method includes receiving a dialog session. The dialog session comprises a set of new inbound messages. The method feeds the dialog session into tokenizer. The method, with the tokenizer, generates a set of tokens by breaking the new inbound messages into a sequence of tokens. The method provides the tokens to a DAG frame labeler cascade. With the DAG frame labeler cascade, the method uses a sequence of tokens to generate a set of token labels. The method passes the token labels and tokens to an entity interpreter. With the entity interpreter, the method generates a DAG frame. With the DAG frame, the method outputs a structured information from a multiturn dialogue.

Abstract: In one aspect, method useful for goal-oriented dialog automation comprising includes the step of receiving an input message. The method includes the step of implementing an entity tagging operation on the input message. The method includes the step of tagging the message context of the input message to generate a tagged message context. The method includes the step of implementing semantic frame extraction from the tagged message context. The method includes the step of implementing an entity interpretation on the extracted frame. The method includes the step of accessing a database to determine a business schedule and a client profile. The business schedule and the client profile are related to the input message. The method includes the step of implementing a retrieval engine. The retrieval engine obtains one or more response templates. The method includes the step of generating a ranked list of candidate templates from the output of the retrieval engine.

Abstract: In one aspect, method useful for goal-oriented dialog automation comprising incudes the step of receiving an input message. The method includes the step of implementing an entity tagging operation on the input message. The method includes the step of tagging the message context of the input message to generate a tagged message context. The method includes the step of implementing semantic frame extraction from the tagged message context. The method includes the step of implementing an entity interpretation on the extracted frame. The method includes the step of accessing a database to determine a business schedule and a client profile. The business schedule and the client profile are related to the input message. The method includes the step of implementing a retrieval engine. The retrieval engine obtains one or more response templates. The method includes the step of generating a ranked list of candidate templates from the output of the retrieval engine.

Abstract: In one aspect, a computer system includes an application implemented with a computer processor that automatically discovers a list items from a set of user data sources, wherein the list items correspond to automatic recommendations for a set of calendar events and tasks, and wherein the list items are discovered programmatically in a set of email conversations and a set of calendar updates. The application extracts the list of items and metadata about the list items from the set of user data sources. The application identifies a type of each list item, wherein a set of types comprises a mandatory-action type and an informative type. The application receives a user created list of items. The application creates an electronic agenda view of the auto-recommended list of items and the user created list of items, and organizes these lists by date.

Abstract: Technologies pertaining to advertisement impression forecasting are described herein. An advertiser sets forth a proposed bid value for a prospective advertisement listing with respect to a keyword for a defined range of time. A number of auctions for the keyword in which the prospective advertisement listing will participate is estimated. A generative model that models auctions for the keyword is sampled to simulate auctions for the keyword, wherein the number of simulated auctions is equivalent to the number of auctions for the keyword in which the prospective advertisement listing is estimated to participate. For each simulated auction, a determination is made regarding whether the prospective advertisement listing wins the auction based upon the proposed bid value set forth by the advertiser. A number of simulated auctions won by the prospective advertiser is output as a forecasted number of impressions for the advertisement over the defined range of time.

Abstract: A classification system is described for resilient classification of data. In various embodiments, the classification system divides a full set of the training data into a positive subset and a negative subset. The positive subset contains all training data with a positive classification value and the negative subset contains all training data with a negative classification value. The classification system constructs several subsets of the training data wherein each subset contains data randomly selected from both the positive subset and the negative subset. The classification system then creates at least two classifiers based on each of the randomly created subsets of the training data.

Abstract: Users make online purchases using a virtual currency. A series of secret encryption keys is generated, where each key in the series is associated with a different epoch. A token tracking table is initialized. Whenever real currency is received from a user wanting to purchase tokens, a semantically secure encryption method is used in conjunction with the secret encryption key in the series that is associated with the current epoch to generate a set of encrypted tokens which includes one or more encrypted paid tokens. The set of encrypted tokens is sent to the user wanting to purchase tokens, and each encrypted paid token in the set is entered into the token tracking table, where the entry for each encrypted paid token includes information specifying that the token has not yet been spent and has not yet been encashed.

Abstract: The prediction of future data events using a generative model is disclosed. One disclosed embodiment comprises a method of predicting a search engine switch, by first tracking a sequence of events in a user search. Next, a search engine switch based upon the sequence of events tracked is predicted. Then, in response to predicting a search engine switch and prior to the user requesting a search engine switch, an action is taken toward changing a user experience.

Abstract: A classification system is described for resiliently classifying data. In various embodiments, the classification system constructs a combined classifier based on multiple classifiers that are constructed to classify a set of training data. The combined classifier can be constructed in parallel with the multiple classifiers and applied to classify data.

Abstract: Techniques described herein help determine dependencies and associations between CPEs in a computing system. These techniques track previous check-ins over a period of time in order to learn the dependencies and associations between CPEs. The previous check-ins are performed by a plurality of different computer programmers. In some embodiments, in response to receiving an indication that a CPE has either already been modified or is about to be modified by a computer programmer, the techniques provide the computer programmer with a recommendation indicating CPEs that are associated with the CPE being modified. This recommendation is based on the dependencies and associations determined from the previous check-ins performed by the plurality of different computer programmers.

Abstract: The prediction of future data events using a generative model is disclosed. One disclosed embodiment comprises a method of predicting a search engine switch, by first tracking a sequence of events in a user search. Next, a search engine switch based upon the sequence of events tracked is predicted. Then, in response to predicting a search engine switch and prior to the user requesting a search engine switch, an action is taken toward changing a user experience.

Abstract: A system for temporal data mining includes a computer readable medium having an application configured to receive at an input module a temporal data series having events with start times and end times, a set of allowed dwelling times and a threshold frequency. The system is further configured to identify, using a candidate identification and tracking module, one or more occurrences in the temporal data series of a candidate episode and increment a count for each identified occurrence. The system is also configured to produce at an output module an output for those episodes whose count of occurrences results in a frequency exceeding the threshold frequency.

Abstract: A system for temporal data mining includes a computer readable medium having an application configured to receive at an input module a temporal data series and a threshold frequency. The system is further configured to identify, using a candidate identification and tracking module, one or more occurrences in the temporal data series of a candidate episode and increment a count for each identified occurrence. The system is also configured to produce at an output module an output for those episodes whose count of occurrences results in a frequency exceeding the threshold frequency.

Abstract: A method, system, and computer program product for fault data correlation in a diagnostic system are provided. The method includes receiving the fault data including a plurality of faults collected over a period of time, and identifying a plurality of episodes within the fault data, where each episode includes a sequence of the faults. The method further includes calculating a frequency of the episodes within the fault data, calculating a correlation confidence of the faults relative to the episodes as a function of the frequency of the episodes, and outputting a report of the faults with the correlation confidence.

Abstract: A method, system, and computer program product for fault data correlation in a diagnostic system are provided. The method includes receiving the fault data including a plurality of faults collected over a period of time, and identifying a plurality of episodes within the fault data, where each episode includes a sequence of the faults. The method further includes calculating a frequency of the episodes within the fault data, calculating a correlation confidence of the faults relative to the episodes as a function of the frequency of the episodes, and outputting a report of the faults with the correlation confidence.

Abstract: A classification system is described for resilient classification of data. In various embodiments, the classification system divides a full set of the training data into a positive subset and a negative subset. The positive subset contains all training data with a positive classification value and the negative subset contains all training data with a negative classification value. The classification system constructs several subsets of the training data wherein each subset contains data randomly selected from both the positive subset and the negative subset. The classification system then creates at least two classifiers based on each of the randomly created subsets of the training data.

Abstract: A classification system is described for resiliently classifying data. In various embodiments, the classification system constructs a combined classifier based on multiple classifiers that are constructed to classify a set of training data. The combined classifier can be constructed in parallel with the multiple classifiers and applied to classify data.

Abstract: A method, system, and apparatus for temporal data mining is disclosed. The method includes receiving as input a temporal data series comprising events with start times and end times, a set of allowed dwelling times, and a threshold frequency. The method also includes finding all frequent principal episodes of a particular length in the temporal data series having dwelling times within the allowed dwelling times. The method includes steps executed in successive passes through the temporal data series.

Abstract: A method, system, and apparatus for temporal data mining is disclosed. The method includes receiving as input a temporal data series comprising time-stamped events, and a threshold frequency. An aspect of this technology is the defining of appropriate frequency counts for non-overlapping and non-interleaved episodes. Two frequency measures and embodiments for obtaining frequent episodes are described. The method includes finding all frequent episodes of a particular length in the temporal data series. The method includes steps executed in successive passes through the temporal data series.