Abstract: A computer-implemented technique can include receiving, at a server, labeled training data including a plurality of groups of words, each group of words having a predicate word, each word having generic word embeddings. The technique can include extracting, at the server, the plurality of groups of words in a syntactic context of their predicate words. The technique can include concatenating, at the server, the generic word embeddings to create a high dimensional vector space representing features for each word. The technique can include obtaining, at the server, a model having a learned mapping from the high dimensional vector space to a low dimensional vector space and learned embeddings for each possible semantic frame in the low dimensional vector space. The technique can also include outputting, by the server, the model for storage, the model being configured to identify a specific semantic frame for an input.

Abstract: A computer-implemented technique can include receiving, at a server, labeled training data including a plurality of groups of words, each group of words having a predicate word, each word having generic word embeddings. The technique can include extracting, at the server, the plurality of groups of words in a syntactic context of their predicate words. The technique can include concatenating, at the server, the generic word embeddings to create a high dimensional vector space representing features for each word. The technique can include obtaining, at the server, a model having a learned mapping from the high dimensional vector space to a low dimensional vector space and learned embeddings for each possible semantic frame in the low dimensional vector space. The technique can also include outputting, by the server, the model for storage, the model being configured to identify a specific semantic frame for an input.

Abstract: A computer-implemented technique can include receiving, at a server, labeled training data including a plurality of groups of words, each group of words having a predicate word, each word having generic word embeddings. The technique can include extracting, at the server, the plurality of groups of words in a syntactic context of their predicate words. The technique can include concatenating, at the server, the generic word embeddings to create a high dimensional vector space representing features for each word. The technique can include obtaining, at the server, a model having a learned mapping from the high dimensional vector space to a low dimensional vector space and learned embeddings for each possible semantic frame in the low dimensional vector space. The technique can also include outputting, by the server, the model for storage, the model being configured to identify a specific semantic frame for an input.

Abstract: Methods, systems, and computer programs are presented for recommending music entities to a user. One method includes defining a set of labels with each label identifying a music concept and constructing at least vector for each of a plurality of entities based on source data. Each vector includes the set of define labels and each label is assigned with a label score. Two vectors respectively associated with two of the plurality of entities are compared. The method further includes generating a recommendation action based on comparison result of the two vectors and transmitting the data for the recommendation action to a device of the user. In one example, the comparisons can be pre-computed and used for the recommendation action.

Abstract: Methods and systems to associate semantically-related items of a plurality of item types using a joint embedding space are disclosed. The disclosed methods and systems are scalable to large, web-scale training data sets. According to an embodiment, a method for associating semantically-related items of a plurality of item types includes embedding training items of a plurality of item types in a joint embedding space configured in a memory coupled to at least one processor, learning one or more mappings into the joint embedding space for each of the item types to create a trained joint embedding space and one or more learned mappings, and associating one or more embedded training items with a first item based upon a distance in the trained joint embedding space from the first item to each said associated embedded training items. Exemplary item types that may be embedded in the joint embedding space include images, annotations, audio and video.

Abstract: Systems and methods provide touristic routes to users. For example, a user at a client device may request a touristic route between an initial and a final destination. A server uses the initial and final destinations to determine a shortest route. The server then defines an envelope around the route in order to identify points of interest. The identified points of interest are ranked and filtered, in order to select the most relevant points of interest. Once the points of interest are selected, the server determines a final route between the initial destination, the points of interest, and the final route. This information is then transmitted to the client device and displayed to the user. The server may also identify and transmit content associated with the final route and/or the points of interest, including, but not limited to, photos, videos, hyperlinks, and advertisements.

Abstract: A server device determines a plurality of images for a query. One or more images, of the plurality of images, are associated with one or more senses of the query. The server device maps the plurality of images into a space by representing the plurality of images with corresponding points in the space; determines one or more hyperplanes in the space based on the corresponding points in the space; calculates one or more scores for the plurality of images based on the corresponding points and the one or more hyperplanes; and ranks the one or more images based on the one or more scores.

Abstract: Methods, systems, and computer programs are presented for recommending music entities to a user. One method includes defining a set of labels with each label identifying a music concept and constructing at least vector for each of a plurality of entities based on source data. Each vector includes the set of define labels and each label is assigned with a label score. Two vectors respectively associated with two of the plurality of entities are compared. The method further includes generating a recommendation action based on comparison result of the two vectors and transmitting the data for the recommendation action to a device of the user. In one example, the comparisons can be pre-computed and used for the recommendation action.

Abstract: Support vector machines are used to classify data contained within a structured dataset such as a plurality of signals generated by a spectral analyzer. The signals are pre-processed to ensure alignment of peaks across the spectra. Similarity measures are constructed to provide a basis for comparison of pairs of samples of the signal. A support vector machine is trained to discriminate between different classes of the samples. to identify the most predictive features within the spectra. In a preferred embodiment feature selection is performed to reduce the number of features that must be considered.

Abstract: A method, computer program product, and computer system for latent collaborative retrieval are described. A first mathematical representation of a query received from a user is generated. A second mathematical representation of a user profile is generated. A plurality of mathematical representations associated with a plurality of items is accessed. The first mathematical representation, the second mathematical representation, and the plurality of mathematical representations are transformed to have a uniform length. A first results subset of items is generated, based upon, at least in part, a first similarity measurement of the first mathematical representation and the plurality of mathematical representations. A second result subset of items is generated based upon, at least in part, a second similarity measurement of the second mathematical representation and the plurality of mathematical representations. A result set of items is generated based upon, at least in part, the first and second result subsets.

Abstract: A method and system for labeling a selected word of a sentence using a deep neural network includes, in one exemplary embodiment, determining an index term corresponding to each feature of the word, transforming the index term or terms of the word into a vector, and predicting a label for the word using the vector. The method and system, in another exemplary embodiment, includes determining, for each word in the sentence, an index term corresponding to each feature of the word, transforming the index term or terms of each word in the sentence into a vector, applying a convolution operation to the vector of the selected word and at least one of the vectors of the other words in the sentence, to transform the vectors into a matrix of vectors, each of the vectors in the matrix including a plurality of row values, constructing a single vector from the vectors in the matrix, and predicting a label for the selected word using the single vector.

Abstract: A method and system for searching for information contained in a database of documents each includes an offline part and an online part. The offline part includes predicting, in a first computer process, semantic data for sentences of the documents contained in the database and storing this data in a database. The online part includes querying the database for information with a semantically-sensitive query, predicting, in a real time computer process, semantic data for the query, and determining, in a second computer process, a matching score against all the documents in the database, which incorporates the semantic data for the sentences and the query.

Abstract: A system and method for determining a similarity between a document and a query includes providing a frequently used dictionary and an infrequently used dictionary in storage memory. For each word or gram in the infrequently used dictionary, n words or grams are correlated from the frequently used dictionary based on a first score. Features for a vector of the infrequently used words or grams are replaced with features from a vector of the correlated words or grams from the frequently used dictionary when the features from a vector of the correlated words or grams meet a threshold value. A similarity score is determined between weight vectors of a query and one or more documents in a corpus by employing the features from the vector of the correlated words or grams that met the threshold value.

Abstract: A system and method for determining a similarity between a document and a query includes building a weight vector for each of a plurality of documents in a corpus of documents stored in memory and building a weight vector for a query input into a document retrieval system. A weight matrix is generated which distinguishes between relevant documents and lower ranked documents by comparing document/query tuples using a gradient step approach. A similarity score is determined between weight vectors of the query and documents in a corpus by determining a product of a document weight vector, a query weight vector and the weight matrix.

Abstract: A network-based system is provided for performing data analysis services using a support vector machine for analyzing data received from a remote user connected to the network. The user transmits a data set to be analyzed and along with an account identifier that allows the analysis service provider to collect payment for the processing services. Once payment has been confirmed, the service provider's server transmits the analysis results to the remote user.

Abstract: A method for training a learning machine for use in discriminative classification and regression includes randomly selecting, in a first computer process, an unclassified datapoint associated with a phenomenon of interest; determining, in a second computer process, a set of datapoints associated with the phenomenon of interest that is likely to be in the same class as the selected unclassified datapoint; predicting, in a third computer process, a class label for the selected unclassified datapoint in a third computer process; predicting a class label for the set of datapoints in a fourth computer process; combining the predicted class labels in a fifth computer process, to predict a composite class label that describes the selected unclassified datapoint and the set of datapoints; and using the combined class label to adjust at least one parameter of the learning machine in a sixth computer process.

Abstract: The invention includes a method for training a learning machine having a deep multi-layered network, with labeled and unlabeled training data. The deep multi-layered network is a network having multiple layers of non-linear mapping. The method generally includes applying unsupervised embedding to any one or more of the layers of the deep network. The unsupervised embedding is operative as a semi-supervised regularizer in the deep network.

Abstract: A system and method for semantic extraction using a neural network architecture includes indexing each word in an input sentence into a dictionary and using these indices to map each word to a d-dimensional vector (the features of which are learned). Together with this, position information for a word of interest (the word to labeled) and a verb of interest (the verb that the semantic role is being predicted for) with respect to a given word are also used. These positions are integrated by employing a linear layer that is adapted to the input sentence. Several linear transformations and squashing functions are then applied to output class probabilities for semantic role labels. All the weights for the whole architecture are trained by backpropagation.

Abstract: Identification of a determinative subset of features from within a group of features is performed by training a support vector machine using training samples with class labels to determine a value of each feature, where features are removed based on their the value. One or more features having the smallest values are removed and an updated kernel matrix is generated using the remaining features. The process is repeated until a predetermined number of features remain which are capable of accurately separating the data into different classes.

Abstract: Methods and systems to associate semantically-related items of a plurality of item types using a joint embedding space are disclosed. The disclosed methods and systems are scalable to large, web-scale training data sets. According to an embodiment, a method for associating semantically-related items of a plurality of item types includes embedding training items of a plurality of item types in a joint embedding space configured in a memory coupled to at least one processor, learning one or more mappings into the joint embedding space for each of the item types to create a trained joint embedding space and one or more learned mappings, and associating one or more embedded training items with a first item based upon a distance in the trained joint embedding space from the first item to each said associated embedded training items. Exemplary item types that may be embedded in the joint embedding space include images, annotations, audio and video.