Abstract: The present disclosure provides systems and methods that perform machine-learned natural language processing. A computing system can include a machine-learned natural language processing model that includes an encoder model trained to receive a natural language text body and output a knowledge graph and a programmer model trained to receive a natural language question and output a program. The computing system can include a computer-readable medium storing instructions that, when executed, cause the processor to perform operations. The operations can include obtaining the natural language text body, inputting the natural language text body into the encoder model, receiving, as an output of the encoder model, the knowledge graph, obtaining the natural language question, inputting the natural language question into the programmer model, receiving the program as an output of the programmer model, and executing the program on the knowledge graph to produce an answer to the natural language question.

Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.

Abstract: The present disclosure provides systems and methods that perform machine-learned natural language processing. A computing system can include a machine-learned natural language processing model that includes an encoder model trained to receive a natural language text body and output a knowledge graph and a programmer model trained to receive a natural language question and output a program. The computing system can include a computer-readable medium storing instructions that, when executed, cause the processor to perform operations. The operations can include obtaining the natural language text body, inputting the natural language text body into the encoder model, receiving, as an output of the encoder model, the knowledge graph, obtaining the natural language question, inputting the natural language question into the programmer model, receiving the program as an output of the programmer model, and executing the program on the knowledge graph to produce an answer to the natural language question.

Abstract: The present disclosure provides systems and methods that perform machine-learned natural language processing. A computing system can include a machine-learned natural language processing model that includes an encoder model trained to receive a natural language text body and output a knowledge graph and a programmer model trained to receive a natural language question and output a program. The computing system can include a computer-readable medium storing instructions that, when executed, cause the processor to perform operations. The operations can include obtaining the natural language text body, inputting the natural language text body into the encoder model, receiving, as an output of the encoder model, the knowledge graph, obtaining the natural language question, inputting the natural language question into the programmer model, receiving the program as an output of the programmer model, and executing the program on the knowledge graph to produce an answer to the natural language question.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying answers to questions using neural networks. One of the methods includes receiving an input text passage and an input question string; processing the input text passage using an encoder neural network to generate a respective encoded representation for each passage token in the input text passage; at each time step: processing a decoder input using a decoder neural network to update the internal state of the decoder neural network; and processing the respective encoded representations and a preceding output of the decoder neural network using a matching vector neural network to generate a matching vector for the time step; and generating an answer score that indicates how well the input text passage answers a question posed by the input question string.

Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.

Abstract: The present disclosure provides systems and methods that perform machine-learned natural language processing. A computing system can include a machine-learned natural language processing model that includes an encoder model trained to receive a natural language text body and output a knowledge graph and a programmer model trained to receive a natural language question and output a program. The computing system can include a computer-readable medium storing instructions that, when executed, cause the processor to perform operations. The operations can include obtaining the natural language text body, inputting the natural language text body into the encoder model, receiving, as an output of the encoder model, the knowledge graph, obtaining the natural language question, inputting the natural language question into the programmer model, receiving the program as an output of the programmer model, and executing the program on the knowledge graph to produce an answer to the natural language question.

Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.

Abstract: Systems and methods are provided for query responding. An exemplary method implementable by one or more computing devices may comprise: receiving a query, wherein the query includes a first sequence of words; converting the query into a second sequence of words by using a first machine learning model; and obtaining a result for the query by applying a second machine learning model to a combination of the first sequence of words and the second sequence of words.

Abstract: Systems and methods are provided for searching historical data. An exemplary method implementable by a computing device, may comprise: obtaining, from a computing device, an audio input; determining a query associated with the audio input based at least on the audio input, wherein the query comprises one or more entities each associated with one or more contents; determining whether the query is related to a historical activity based at lease on the one or more entities each associated with the one or more contents; and in response to determining that the query is related to a historical activity, searching historical data based on the query associated with the audio input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a system output from a system input using a neural network system comprising an encoder neural network configured to, for each of a plurality of encoder time steps, receive an input sequence comprising a respective question token, and process the question token at the encoder time step to generate an encoded representation of the question token, and a decoder neural network configured to, for each of a plurality of decoder time steps, receive a decoder input, and process the decoder input and a preceding decoder hidden state to generate an updated decoder hidden state.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying answers to questions using neural networks. One of the methods includes receiving an input text passage and an input question string; processing the input text passage using an encoder neural network to generate a respective encoded representation for each passage token in the input text passage; at each time step: processing a decoder input using a decoder neural network to update the internal state of the decoder neural network; and processing the respective encoded representations and a preceding output of the decoder neural network using a matching vector neural network to generate a matching vector for the time step; and generating an answer score that indicates how well the input text passage answers a question posed by the input question string.

Abstract: A model generation module is described herein for using a machine learning technique to generate a model for use by a search engine. The model assists the search engine in generating alterations of search queries, so as to improve the relevance and performance of the search queries. The model includes a plurality of features having weights and levels of uncertainty associated therewith, where each feature defines a rule for altering a search query in a defined manner when a context condition, specified by the rule, is present. The model generation module generates the model based on user behavior information, including query reformulation information and user preference information. The query reformulation information indicates query reformulations made by at least one agent (such as users). The preference information indicates at extent to which the users were satisfied with the query reformulations.