Patent application number | Description | Published |
20090204605 | Semantic Search Via Role Labeling - 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. | 08-13-2009 |
20100179933 | SUPERVISED SEMANTIC INDEXING AND ITS EXTENSIONS - 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. | 07-15-2010 |
20100185659 | SUPERVISED SEMANTIC INDEXING AND ITS EXTENSIONS - 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. | 07-22-2010 |
Patent application number | Description | Published |
20110301942 | Method and Apparatus for Full Natural Language Parsing - The method and apparatus for discriminative natural language parsing, uses a deep convolutional neural network adapted for text and a structured tag inference in a graph. In the method and apparatus, a trained recursive convolutional graph transformer network, formed by the deep convolutional neural network and the graph, predicts “levels” of a parse tree based on predictions of previous levels. | 12-08-2011 |
20120253792 | Sentiment Classification Based on Supervised Latent N-Gram Analysis - A method for sentiment classification of a text document using high-order n-grams utilizes a multilevel embedding strategy to project n-grams into a low-dimensional latent semantic space where the projection parameters are trained in a supervised fashion together with the sentiment classification task. Using, for example, a deep convolutional neural network, the semantic embedding of n-grams, the bag-of-occurrence representation of text from n-grams, and the classification function from each review to the sentiment class are learned jointly in one unified discriminative framework. | 10-04-2012 |
20120275690 | DISTRIBUTED ARTIFICIAL INTELLIGENCE SERVICES ON A CELL PHONE - A cell phone having distributed artificial intelligence services is provided. The cell phone includes a neural network for performing a first pass of object recognition on an image to identify objects of interest therein based on one or more criterion. The cell phone also includes a patch generator for deriving patches from the objects of interest. Each of the patches includes a portion of a respective one of the objects of interest. The cell phone additionally includes a transmitter for transmitting the patches to a server for further processing in place of an entirety of the image to reduce network traffic. | 11-01-2012 |
20120310627 | DOCUMENT CLASSIFICATION WITH WEIGHTED SUPERVISED N-GRAM EMBEDDING - Methods and systems for document classification include embedding n-grams from an input text in a latent space, embedding the input text in the latent space based on the embedded n-grams and weighting said n-grams according to spatial evidence of the respective n-grams in the input text, classifying the document along one or more axes, and adjusting weights used to weight the n-grams based on the output of the classifying step. | 12-06-2012 |
20140122388 | QUERY GENERATION AND TIME DIFFERENCE FEATURES FOR SUPERVISED SEMANTIC INDEXING - Semantic indexing methods and systems are disclosed. One such method is directed to training a semantic indexing model by employing an expanded query. The query can be expanded by merging the query with documents that are relevant to the query for purposes of compensating for a lack of training data. In accordance with another exemplary aspect, time difference features can be incorporated into a semantic indexing model to account for changes in query distributions over time. | 05-01-2014 |
20140236577 | Semantic Representations of Rare Words in a Neural Probabilistic Language Model - Systems and methods are disclosed for representing a word by extracting n-dimensions for the word from an original language model; if the word has been previously processed, use values previously chosen to define an (n+m) dimensional vector and otherwise randomly selecting m values to define the (n+m) dimensional vector; and applying the (n+m) dimensional vector to represent words that are not well-represented in the language model. | 08-21-2014 |
20140236578 | Question-Answering by Recursive Parse Tree Descent - Systems and methods are disclosed to answer free form questions using recursive neural network (RNN) by defining feature representations at every node of a parse trees of questions and supporting sentences, when applied recursively, starting with token vectors from a neural probabilistic language model; and extracting answers to arbitrary natural language questions from supporting sentences. | 08-21-2014 |
20140310218 | High-Order Semi-RBMs and Deep Gated Neural Networks for Feature Interaction Identification and Non-Linear Semantic Indexing - Systems and method are disclosed for determining complex interactions among system inputs by using semi-Restricted Boltzmann Machines (RBMs) with factorized gated interactions of different orders to model complex interactions among system inputs; applying semi-RBMs to train a deep neural network with high-order within-layer interactions for learning a distance metric and a feature mapping; and tuning the deep neural network by minimizing margin violations between positive query document pairs and corresponding negative pairs. | 10-16-2014 |
Patent application number | Description | Published |
20090258779 | Regeneration and rejuvenation of supported hydroprocessing catalysts - Methods for rejuvenation of supported metallic catalysts comprised of a Group VIII metal, a Group VIB metal, making use of these metals, an organic complexing agent, and optionally an organic additive, are provided. The rejuvenation includes stripping and regeneration of a spent or partially spent catalyst, followed by impregnation with metals and at least one organic compound. The impregnated, regenerated catalysts are dried, calcined, and sulfided. The catalysts are used for hydroprocessing, particularly hydrodesulfurization and hydrodenitrogenation, of hydrocarbon feedstocks. | 10-15-2009 |
20090261019 | Hydroprocessing using rejuvenated supported hydroprocessing catalysts - Methods for hydroprocessing of hydrocarbon feedstocks, including hydrodesulfurization and hydrodenitrogenation, using rejuvenated supported metallic catalysts are provided. The supported metallic catalysts comprised of a Group VIII metal, a Group VIB metal, are rejuvenated by a process making use of these metals, an organic complexing agent, and optionally an organic additive. The rejuvenation includes stripping and regeneration of a spent or partially spent catalyst, followed by impregnation with metals and at least one organic compound. The impregnated, regenerated catalysts are dried, calcined, and sulfided. | 10-22-2009 |
20100012554 | Selective Catalysts For Naphtha Hydrodesulfurization - Naphtha is selectively hydrodesulfurized with retention of olefin content. More particularly, a CoMo metal hydrogenation component is loaded on a silica or modified silica support in the presence of an organic additive to produce a catalyst which is then used for hydrodesulfurizing naphtha while retaining olefins. | 01-21-2010 |
20100093522 | Bulk catalysts having increased stability - Bulk catalysts that include a Group VI metal, a Group VIII metal, and at least 10-60% of an organic compound based component are formed. The bulk catalysts have increased stability through the use of a stabilizer in the organic compound based component, the use of an improved gas phase sulfidation, or a combination thereof. The bulk catalysts are suitable for hydroprocessing of hydrocarbon feeds. | 04-15-2010 |
20100320123 | Selective Catalysts Having Silica Supports For Naphtha Hydrodesulfurization - A method for hydrodesulfurizing FCC naphtha is described. More particularly, a Co/Mo metal hydrogenation component is loaded on a silica or modified silica support in the presence of organic ligand and sulfided to produce a catalyst which is then used for hydrodesulfurizing FCC naphtha. The silica support has a defined pore size distribution which minimizes olefin saturation. | 12-23-2010 |
20120111767 | INTERSTITIAL METAL HYDRIDE CATALYST SYSTEMS AND ASSOCIATED PROCESSES - Exemplary embodiments of the present invention relate to the processing of hydrocarbon-containing feedstreams in the presence of an interstitial metal hydride containing catalyst comprising a surface, and a Group VI/Group VIII metal sulfide coated onto the surface of the interstitial metal hydride. The catalysts and processes of the present invention can improve overall hydrogenation, product conversion, as well as sulfur reduction in hydrocarbon feedstreams. | 05-10-2012 |
20120115713 | POISON RESISTANT CATALYST SYSTEMS AND ASSOCIATED PROCESSES - Exemplary embodiments of the present invention relate to the processing of hydrocarbon-containing feedstreams in the presence of an active catalyst component comprising a surface, and a metal oxide film coated on the surface of the active catalyst component. The catalysts and processes of the present invention can improve overall hydrogenation, product conversion, as well as improved resistance to catalytic deactivation due to sulfur and nitrogen compounds present in the hydrocarbon feedstreams. | 05-10-2012 |
20140081060 | INTERSTITIAL METAL HYDRIDE CATALYST SYSTEMS AND ASSOCIATED PROCESSES - Exemplary embodiments of the present invention relate to the processing of hydrocarbon-containing feedstreams in the presence of an interstitial metal hydride containing catalyst comprising a surface, and a Group VI/Group VIII metal sulfide coated onto the surface of the interstitial metal hydride. The catalysts and processes of the present invention can improve overall hydrogenation, product conversion, as well as sulfur reduction in hydrocarbon feedstreams. | 03-20-2014 |
20140275606 | Methyl-Substituted Biphenyl Compounds, Their Production and Their Use in the Manufacture of Plasticizers - In a process for producing a methyl-substituted biphenyl compound, at least one methyl-substituted cyclohexylbenzene compound of the formula: | 09-18-2014 |
20140275607 | Methyl-Substituted Biphenyl Compounds, Their Production and Their Use in the Manufacture of Plasticizers - In a process for producing a methyl-substituted biphenyl compound, at least one methyl-substituted cyclohexylbenzene compound of the formula: | 09-18-2014 |