Abstract: Domain-specific language understanding models that may be built, tested and improved quickly and efficiently are provided. Methods, systems and devices are provided that enable a developer to build user intent detection models, language entity extraction models, and language entity resolution models quickly and without specialized machine learning knowledge. These models may be built and implemented via single model systems that enable the models to be built in isolation or in an end-to-end pipeline system that enables the models to be built and improved in a simultaneous manner.

Abstract: Domain-specific language understanding models that may be built, tested and improved quickly and efficiently are provided. Methods, systems and devices are provided that enable a developer to build user intent detection models, language entity extraction models, and language entity resolution models quickly and without specialized machine learning knowledge. These models may be built and implemented via single model systems that enable the models to be built in isolation or in an end-to-end pipeline system that enables the models to be built and improved in a simultaneous manner.

Abstract: Domain-specific language understanding models that may be built, tested and improved quickly and efficiently are provided. Methods, systems and devices are provided that enable a developer to build user intent detection models, language entity extraction models, and language entity resolution models quickly and without specialized machine learning knowledge. These models may be built and implemented via single model systems that enable the models to be built in isolation or in an end-to-end pipeline system that enables the models to be built and improved in a simultaneous manner.

Abstract: A system is provided that trains a spoken language understanding (SLU) classifier. A corpus of user utterances is received. For each of the user utterances in the corpus, the user utterance is semantically parsed, and the result of this semantic parsing is represented as a rooted semantic parse graph. The parse graphs representing all of the user utterances in the corpus are then combined into a single corpus graph that represents the semantic parses of the entire corpus. The user utterances in the corpus are then clustered into intent-wise homogeneous groups of user utterances, where this clustering includes finding subgraphs in the corpus graph that represent different groups of user utterances, and each of these different groups has a similar user intent. The intent-wise homogeneous groups of user utterances are then used to train the SLU classifier, and the trained SLU classifier is output.

Abstract: A dialog state tracking system. One aspect of the system is the use of multiple utterance decoders and/or multiple spoken language understanding (SLU) engines generating competing results that improve the likelihood that the correct dialog state is available to the system and provide additional features for scoring dialog state hypotheses. An additional aspect is training a SLU engine and a dialog state scorer/ranker DSR engine using different subsets from a single annotated training data set. A further aspect is training multiple SLU/DSR engine pairs from inverted subsets of the annotated training data set. Another aspect is web-style dialog state ranking based on dialog state features using discriminative models with automatically generated feature conjunctions. Yet another aspect is using multiple parameter sets with each ranking engine and averaging the rankings. Each aspect independently improves dialog state tracking accuracy and may be combined in various combinations for greater improvement.

Abstract: Systems and methods for using Internet service co-branded financial instruments are disclosed. In one embodiment, a method for using Internet co-branded financial instruments may include: (1) a financial institution and a provider of an Internet service establishing a relationship, which may be a co-branded financial instrument, such as a credit card; (2) a user receiving the co-branded financial instrument; (3) the provider of the Internet service monitoring the user's Internet service use; (4) the provider of the Internet service may provide the user's Internet service use to the financial institution; (5) the financial institution issuing rewards to the user's account based on the Internet service use; (6) the financial institution may provide the provider of the Internet service with financial information for the user; and (7) the provider of the Internet service may charge an advertiser for ad placement based on the user financial information.

Abstract: Disclosed herein are technologies directed to discovering semantic similarities between images and text, which can include performing image search using a textual query, performing text search using an image as a query, and/or generating captions for images using a caption generator. A semantic similarity framework can include a caption generator and can be based on a deep multimodal similar model. The deep multimodal similarity model can receive sentences and determine the relevancy of the sentences based on similarity of text vectors generated for one or more sentences to an image vector generated for an image. The text vectors and the image vector can be mapped in a semantic space, and their relevance can be determined based at least in part on the mapping. The sentence associated with the text vector determined to be the most relevant can be output as a caption for the image.

Abstract: A system is provided that trains a spoken language understanding (SLU) classifier. A corpus of user utterances is received. For each of the user utterances in the corpus, the user utterance is semantically parsed, and the result of this semantic parsing is represented as a rooted semantic parse graph. The parse graphs representing all of the user utterances in the corpus are then combined into a single corpus graph that represents the semantic parses of the entire corpus. The user utterances in the corpus are then clustered into intent-wise homogeneous groups of user utterances, where this clustering includes finding subgraphs in the corpus graph that represent different groups of user utterances, and each of these different groups has a similar user intent. The intent-wise homogeneous groups of user utterances are then used to train the SLU classifier, and the trained SLU classifier is output.

Abstract: Disclosed herein are technologies directed to discovering semantic similarities between images and text, which can include performing image search using a textual query, performing text search using an image as a query, and/or generating captions for images using a caption generator. A semantic similarity framework can include a caption generator and can be based on a deep multimodal similar model. The deep multimodal similarity model can receive sentences and determine the relevancy of the sentences based on similarity of text vectors generated for one or more sentences to an image vector generated for an image. The text vectors and the image vector can be mapped in a semantic space, and their relevance can be determined based at least in part on the mapping. The sentence associated with the text vector determined to be the most relevant can be output as a caption for the image.

Abstract: A system is described herein which uses a neural network having an input layer that accepts an input vector and a feature vector. The input vector represents at least part of input information, such as, but not limited to, a word or phrase in a sequence of input words. The feature vector provides supplemental information pertaining to the input information. The neural network produces an output vector based on the input vector and the feature vector. In one implementation, the neural network is a recurrent neural network. Also described herein are various applications of the system, including a machine translation application.

Abstract: Domain-specific language understanding models that may be built, tested and improved quickly and efficiently are provided. Methods, systems and devices are provided that enable a developer to build user intent detection models, language entity extraction models, and language entity resolution models quickly and without specialized machine learning knowledge. These models may be built and implemented via single model systems that enable the models to be built in isolation or in an end-to-end pipeline system that enables the models to be built and improved in a simultaneous manner.

Abstract: A database having listings rather than long documents is searched using a term frequency-inverse document frequency (Tf/Idf) algorithm.

Abstract: A dialog state tracking system. One aspect of the system is the use of multiple utterance decoders and/or multiple spoken language understanding (SLU) engines generating competing results that improve the likelihood that the correct dialog state is available to the system and provide additional features for scoring dialog state hypotheses. An additional aspect is training a SLU engine and a dialog state scorer/ranker DSR engine using different subsets from a single annotated training data set. A further aspect is training multiple SLU/DSR engine pairs from inverted subsets of the annotated training data set. Another aspect is web-style dialog state ranking based on dialog state features using discriminative models with automatically generated feature conjunctions. Yet another aspect is using multiple parameter sets with each ranking engine and averaging the rankings. Each aspect independently improves dialog state tracking accuracy and may be combined in various combinations for greater improvement.

Abstract: A document that includes a representation of a two-dimensional (2-D) image may be obtained. A selection indicator indicating a selection of at least a portion of the 2-D image may be obtained. A match correspondence may be determined between the selected portion of the 2-D image and a three-dimensional (3-D) image object stored in an object database, the match correspondence based on a web crawler analysis result. A 3-D rendering of the 3-D image object that corresponds to the selected portion of the 2-D image may be initiated.

Abstract: The subject disclosure is directed towards automated processes for generating sentence completion questions based at least in part on a language model. Using the language model, a sentence is located, and alternates for a focus word (or words) in the sentence are automatically provided. Also described is automated filtering candidate sentences to locate the sentence, filtering the alternates based upon elimination criteria, scoring sentences with the correct word and as modified the alternates, and ranking the alternates. Manual selection may be used along with the automated processes.

Abstract: Described is a technology by which a structured model of repetition is used to determine the words spoken by a user, and/or a corresponding database entry, based in part on a prior utterance. For a repeated utterance, a joint probability analysis is performed on (at least some of) the corresponding word sequences as recognized by one or more recognizers) and associated acoustic data. For example, a generative probabilistic model, or a maximum entropy model may be used in the analysis. The second utterance may be a repetition of the first utterance using the exact words, or another structural transformation thereof relative to the first utterance, such as an extension that adds one or more words, a truncation that removes one or more words, or a whole or partial spelling of one or more words.

Abstract: A system is described herein which uses a neural network having an input layer that accepts an input vector and a feature vector. The input vector represents at least part of input information, such as, but not limited to, a word or phrase in a sequence of input words. The feature vector provides supplemental information pertaining to the input information. The neural network produces an output vector based on the input vector and the feature vector. In one implementation, the neural network is a recurrent neural network. Also described herein are various applications of the system, including a machine translation application.

Abstract: The subject disclosure is directed towards automated processes for generating sentence completion questions based at least in part on a language model. Using the language model, a sentence is located, and alternates for a focus word (or words) in the sentence are automatically provided. Also described is automated filtering candidate sentences to locate the sentence, filtering the alternates based upon elimination criteria, scoring sentences with the correct word and as modified the alternates, and ranking the alternates. Manual selection may be used along with the automated processes.

Abstract: A document-term matrix may be generated based on a corpus. A term representation matrix may be generated based on modifying a plurality of elements of the document-term matrix based on antonym information included in the corpus. Similarities may be determined based on a plurality of elements of the term representation matrix.

Abstract: A document that includes a representation of a two-dimensional (2-D) image may be obtained. A selection indicator indicating a selection of at least a portion of the 2-D image may be obtained. A match correspondence may be determined between the selected portion of the 2-D image and a three-dimensional (3-D) image object stored in an object database, the match correspondence based on a web crawler analysis result. A 3-D rendering of the 3-D image object that corresponds to the selected portion of the 2-D image may be initiated.