Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: A new multifunctional biomass suspension deflagration test-bed is provided, which includes a closed combustion chamber. An integrated temperature and pressure sensor is arranged in the combustion chamber, and a high-speed camera and a laser concentration-measuring instrument are arranged outside the combustion chamber, which can monitor suspension deflagration. A bottom of the combustion chamber is provided with a hollow mushroom-shaped dispersion nozzle with a tray. A nozzle body is provided with a gas main-flow channel at a center thereof and gas deflected-flow channels arranged around the gas main-flow channel. A mushroom-shaped baffle plate is arranged above the nozzle body. The gas main-flow channel extends upward to the mushroom-shaped baffle plate. A vent hole is formed in a portion of the mushroom-shaped baffle plate which is corresponding to the gas main-flow channel. Each gas deflected-flow channel is inclined outward from bottom to top and directed to the mushroom-shaped baffle plate.

Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: A method for applying a trained machine learning model to answer a user query comprises receiving a query text from a user. A previously-trained discriminator is received, the previously-trained discriminator configured to output, for a pair of sentences, a match value indicating a quality of semantic match between the pair of sentences. For each candidate answer text of a plurality of candidate answer texts, the previously-trained discriminator is operated to output a candidate match value for the query text and the candidate answer text based on comparing a first hierarchy of representations of the query text at increasing degrees of semantic compression to a second hierarchy of representations of the candidate answer text at increasing degrees of semantic compression. An answer text is output that is associated with a highest candidate match value among candidate match values.

Abstract: A new multifunctional biomass suspension deflagration test-bed is provided, which includes a closed combustion chamber. An integrated temperature and pressure sensor is arranged in the combustion chamber, and a high-speed camera and a laser concentration-measuring instrument are arranged outside the combustion chamber, which can monitor suspension deflagration. A bottom of the combustion chamber is provided with a hollow mushroom-shaped dispersion nozzle with a tray. A nozzle body is provided with a gas main-flow channel at a center thereof and gas deflected-flow channels arranged around the gas main-flow channel. A mushroom-shaped baffle plate is arranged above the nozzle body. The gas main-flow channel extends upward to the mushroom-shaped baffle plate. A vent hole is formed in a portion of the mushroom-shaped baffle plate which is corresponding to the gas main-flow channel. Each gas deflected-flow channel is inclined outward from bottom to top and directed to the mushroom-shaped baffle plate.

Abstract: A method for estimating a quality of semantic match of a first sentence to a second sentence comprises outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, outputting a second hierarchy of representations of the second sentence at increasing degrees of semantic compression, comparing a selected representation in the first hierarchy to each of a plurality of representations in the second hierarchy, comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy, and outputting a match value indicating a quality of semantic match between the first sentence and the second sentence, the match value based at least on the comparisons.

Abstract: A method for estimating a quality of semantic match of a first sentence to a second sentence comprises outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, outputting a second hierarchy of representations of the second sentence at increasing degrees of semantic compression, comparing a selected representation in the first hierarchy to each of a plurality of representations in the second hierarchy, comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy, and outputting a match value indicating a quality of semantic match between the first sentence and the second sentence, the match value based at least on the comparisons.

Abstract: A method for estimating a quality of semantic match of a first sentence to a second sentence comprises outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, outputting a second hierarchy of representations of the second sentence at increasing degrees of semantic compression, comparing a selected representation in the first hierarchy to each of a plurality of representations in the second hierarchy, comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy, and outputting a match value indicating a quality of semantic match between the first sentence and the second sentence, the match value based at least on the comparisons.

Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: A software tool for organizing and manipulating an electronic document comprising at least one group of document pages, comprises a first user interface module configured to present the document pages of the electronic document in a list-like arrangement; a second user interface module configured to present the document pages of each group in a respective panel; and means operable to manipulate a plurality of selected document pages presented in one or more of the panels simultaneously.