Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more expert neural network blocks that each include router that performs expert-choice routing between multiple expert neural networks.

Abstract: A method includes providing a first set of data objects to a first skip router of a neural network (NN). The NN includes a first NN layer and a second NN layer. The first set of data objects is subdivided into a first set of skip objects and a first set of non-skip objects based on a first skip logic implemented by the first skip router and a first context of each data object in the first set of data objects. A first set of processed objects is generated based on the first set of non-skip objects and a first layer logic implemented by the first NN layer. Predictions are generated based on a second set of data objects and a second layer logic implemented by the second NN layer. The second set of data objects includes the first set of processed objects and the first set of skip objects.

Abstract: A company may implement automated workflows for convenience of users or to reduce support costs. For example, allowing a user to change an address using an automated workflow may be faster or less expensive than with a human agent. In some instances, a first communications session may be started between a first user and a second user. During the first communications session, one or more communications may be processed to select an intent of the first user and a value of an information item communicated by the first user. An automated workflow may be selected to continue assisting the first user, and the first user may be transferred to a second communications session with the automated workflow. The automated workflow may be initialized with the value of the information item that was provided during the first communications session so that the first user does not need to repeat information.

Abstract: A description of a conversation may be generated to allow a person to understand important aspects of the conversation without needing to review the conversation. The conversation description may be generated by identifying one or more events that occurred in the conversation and then generating the description using the identified events. A set of possible events may be determined in advance for a particular application. The events may be identified by using an event neural network for each event. Each event neural network may process the messages of the conversation to generate an event score that indicates a match between the conversation and the corresponding event. The event scores may then be used to select one or more events. Message scores from the event neural network of a selected event may then be used to select one or more messages of the conversation as a rationale for the selected event.

Abstract: A parallel core simulation device for commingling production in low-permeability gas reservoirs includes a gas supercharger configured to provide a high pressure gas to simulate a fluid in a gas reservoir, a plurality of core holders arranged in parallel, a thermostat configured to control a temperature of each core holder to simulate a temperature of the gas reservoir, a pressure pump configured to control a pressure applied to each core holder to simulate a confining pressure of the gas reservoir, a first back-pressure valve communicated with each core holder, a fully-automatic gas meter configured to measure a rate and a volume of gas production and a second hydraulic pump configured to simulate a part of a gas well Christmas Tree.

Abstract: The amount of time required to train a neural network may be decreased by modifying the neural network to allow for greater parallelization of computations. The computations for cells of the neural network may be modified so that the matrix-vector multiplications of the cell do not depend on a previous cell and thus allowing the matrix-vector computations to be performed outside of the cells. Because the matrix-vector multiplications can be performed outside of the cells, they can be performed in parallel to decrease the computation time required for processing a sequence of training vectors with the neural network. The trained neural network may be applied to a wide variety of applications, such as performing speech recognition, determining a sentiment of text, determining a subject matter of text, answering a question in text, or translating text to another language.

Abstract: The present invention belongs to the technical field of oil and gas field development, and discloses a method for calculating a single-well controlled reserve of a low-permeability/tight gas reservoir and analyzing residual gas thereof. The method includes: calculating a reserve controlled by each gas well in a block by using a gas reservoir dynamic reserve calculation method; establishing a new reserve calculation formula for solution and comparative analysis by an example; and quantitatively analyzing an effect of a startup pressure gradient and a stress sensitivity on a calculation result of the single-well controlled reserve, wherein the analysis of the factors affecting reserve calculation shows that, when the startup pressure gradient reaches 0.02 MPa/m, the calculated reserve is significantly reduced compared with a conventional method, but when the startup pressure gradient is greater than 0.1 MPa/m, the effect gradually stabilizes.

Abstract: A company may implement automated workflows for convenience of users or to reduce support costs. For example, allowing a user to change an address using an automated workflow may be faster or less expensive than with a human agent. In some instances, a first communications session may be started between a first user and a second user. During the first communications session, one or more communications may be processed to select an intent of the first user and a value of an information item communicated by the first user. An automated workflow may be selected to continue assisting the first user, and the first user may be transferred to a second communications session with the automated workflow. The automated workflow may be initialized with the value of the information item that was provided during the first communications session so that the first user does not need to repeat information.

Abstract: Text may be modified according to a specified attribute value, such as changing a 1-star review to a 5-star review. To modify the text, an input sequence of tokens may be obtained corresponding to the text. Mask scores may be computed for the tokens by processing the input sequence of tokens with masking neural network. One or more tokens may be selected using the mask scores, and a masked sequence of tokens may be generated by replacing the selected tokens with a mask token. The masked sequence of tokens may be processed by a language model neural network to select a replacement token for each of the mask tokens. Modified text may then be generated using the selected replacement tokens. The modified text may be used for any appropriate application, such as suggesting messages to users participating in a conversation.

Abstract: A user of an automated natural language system may submit an ambiguous or incomplete request, and interactive techniques may be used to obtain clarification information from the user and then determine a response for presentation to the user. A user's initial request may be processed to compute a category score for each possible category of request. The category scores may be processed to determine if clarification of the request is needed. Where clarification is needed, one or more tags may be selected to determine a clarification question to be presented to the user. For example, a tag clarification score may be computed for each tag that indicates a value of the tag in clarifying the request. After receiving the clarification information from the user, one or more categories may be selected or, where needed, additional clarification information may be obtained.

Abstract: A company may implement automated workflows for convenience of users or to reduce support costs. For example, allowing a user to change an address using an automated workflow may be faster or less expensive than with a human agent. Companies may provide support over different types of communications channels with different capabilities, such as voice channels and text channels. Instead of implementing different workflows for different channels, a company may separate aspects of the workflow that are common to different channels from aspects of the workflow that are different for different channels. For example, a workflow may be implemented to determine an action in response to a received communication where the action may be used with multiple channels. The action may then be used to select an action implementation that is specific to a channel.

Abstract: A company may implement automated workflows for convenience of users or to reduce support costs. For example, allowing a user to change an address using an automated workflow may be faster or less expensive than with a human agent. In some instances, a first communications session may be started between a first user and a second user. During the first communications session, one or more communications may be processed to select an intent of the first user and a value of an information item communicated by the first user. An automated workflow may be selected to continue assisting the first user, and the first user may be transferred to a second communications session with the automated workflow. The automated workflow may be initialized with the value of the information item that was provided during the first communications session so that the first user does not need to repeat information.

Abstract: A message may be suggested to a user participating in a conversation using one or more neural networks where the suggested message is adapted to the preferences or communication style of the user. The suggested message may be adapted to the user with a user embedding vector that represents the preferences or communication style of the user in a vector space. To suggest a message to the user, a conversation feature vector may be computed by processing the text of the conversation with a neural network. A context score may be computed for one or more designated messages, where the context score is computed by processing the user embedding vector, the conversation feature vector, and a designated message feature vector with a neural network. A designated message may be selected as a suggested message for the user using the context scores. The suggestion may then be presented to the user.

Abstract: A message may be suggested to a user participating in a conversation using one or more neural networks where the suggested message is adapted to the preferences or communication style of the user. The suggested message may be adapted to the user with a user embedding vector that represents the preferences or communication style of the user in a vector space. To suggest a message to the user, a conversation feature vector may be computed by processing the text the conversation with a neural network. A context score may be computed for one or more designated messages, where the context score is computed by processing the user embedding vector, the conversation feature vector, and a designated message feature vector with a neural network. A designated message may be selected as a suggested message for the user using the context scores. The suggestion may then presented to the user.

Abstract: Machine learning models may be used during a communications session to process natural language communications and perform actions relating to the communications session. For example, a machine learning model may be used to provide an automated response to a user, to suggest a completion of text being entered by a user, or to provide information about a relevant resource. Machine learning models may rely on machine learning model data that is updated during a communications session as communications are processed by the machine learning model. To improve the performance of a machine learning model when a user leaves a first communications session and enters a second communications session, the machine learning model data may be stored during a first communications session and then retrieved during the second communications session to initialize a machine learning model for the second communications session.

Abstract: The present disclosure describes a system, method, and computer program for matching an input file to one of a plurality of datastore files and displaying the rationale for the match. Neural networks are trained to create vector representations of objects in the input file and the datastore files. The cost of each possible pairing of vector representations between the input file and a datastore file is computed, and an optimal transport algorithm is used to identify the vector pairings that result in the lowest total cost of alignment. The datastore file with the lowest total cost of alignment to the input file is identified as the best matching file. The alignment results are used to display the rationale for the match. To constrain the alignment results of the optimal transport algorithm, one or more dummy points and, in certain embodiments, duplicate points are added to one or both of the vector sets to achieve alignments with the desired sparsity patterns.

Abstract: Text of an incomplete message entered by a user may be processed using a neural network to suggest messages similar to the message the user is in the process of entering. Word embeddings may be obtained for the words of the text that represent the words in a first vector space. The word embeddings may then be processed by the neural network to compute an input message feature vector that represents the incomplete message in a second vector space. The input message feature vector may be used to select a first designated message as a suggestion from a set of designated messages, and the first designated message may be selected using a similarity score computed from the input message feature vector and a first designated message feature vector corresponding to the first designated message. The first designated message may then be presented as a suggestion to the user.

Abstract: The amount of time required to train a neural network may be decreased by modifying the neural network to allow for greater parallelization of computations. The computations for cells of the neural network may be modified so that the matrix-vector multiplications of the cell do not depend on a previous cell and thus allowing the matrix-vector computations to be performed outside of the cells. Because the matrix-vector multiplications can be performed outside of the cells, they can be performed in parallel to decrease the computation time required for processing a sequence of training vectors with the neural network. The trained neural network may be applied to a wide variety of applications, such as performing speech recognition, determining a sentiment of text, determining a subject matter of text, answering a question in text, or translating text to another language.

Abstract: The amount of time required to train a neural network may be decreased by modifying the neural network to allow for greater parallelization of computations. The computations for cells of the neural network may be modified so that the matrix-vector multiplications of the cell do not depend on a previous cell and thus allowing the matrix-vector computations to be performed outside of the cells. Because the matrix-vector multiplications can be performed outside of the cells, they can be performed in parallel to decrease the computation time required for processing a sequence of training vectors with the neural network. The trained neural network may be applied to a wide variety of applications, such as performing speech recognition, determining a sentiment of text, determining a subject matter of text, answering a question in text, or translating text to another language.

Abstract: Text may be modified according to a specified attribute value, such as changing a 1-star review to a 5-star review. To modify the text, an input sequence of tokens may be obtained corresponding to the text. Mask scores may be computed for the tokens by processing the input sequence of tokens with masking neural network. One or more tokens may be selected using the mask scores, and a masked sequence of tokens may be generated by replacing the selected tokens with a mask token. The masked sequence of tokens may be processed by a language model neural network to select a replacement token for each of the mask tokens. Modified text may then be generated using the selected replacement tokens. The modified text may be used for any appropriate application, such as suggesting messages to users participating in a conversation.