Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for planning the future trajectory of an autonomous vehicle in an environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network. In one aspect, a method for training a policy neural network configured to receive a scene data input and to generate a policy output to be followed by a target agent comprises: maintaining a set of training data, the set of training data comprising (i) training scene inputs and (ii) respective target policy outputs; at each training iteration: generating additional training scene inputs; generating a respective target policy output for each additional training scene input using a trained expert policy neural network that has been trained to receive an expert scene data input comprising (i) data characterizing the current scene and (ii) data characterizing a future state of the target agent; updating the set of training data; and training the policy neural network on the updated set of training data.

Abstract: A method for performing one or more tasks, wherein each of the one or more tasks includes predicting behavior of one or more agents in an environment, the method comprising: obtaining a three-dimensional (3D) input tensor representing behaviors of the one or more agents in the environment across a plurality of time steps; generating an encoded representation of the 3D input tensor by processing the 3D input tensor using an encoder neural network, wherein 3D input tensor comprises a plurality of observed cells and a plurality of masked cells; and processing the encoded representation of the 3D input tensor using a decoder neural network to generate a 4D output tensor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating dependency parses for input text segments, which may be provided as inputs to a natural language processing system. One of the systems includes a first neural network comprising: one or more initial neural network layers configured to, for each token in an input text sequence: receive features for the token; and collectively process the features to generate an alternative representation of the features for use in determining a part of speech of the token in the input text sequence; and a dependency parsing neural network configured to: process the alternative representations of the features for the tokens in the input text sequence generated by the one or more initial neural network layers to generate a dependency parse of the input text sequence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating dependency parses for input text segments, which may be provided as inputs to a natural language processing system. One of the systems includes a first neural network comprising: one or more initial neural network layers configured to, for each token in an input text sequence: receive features for the token; and collectively process the features to generate an alternative representation of the features for use in determining a part of speech of the token in the input text sequence; and a dependency parsing neural network configured to: process the alternative representations of the features for the tokens in the input text sequence generated by the one or more initial neural network layers to generate a dependency parse of the input text sequence.

Abstract: A system and associated methods are provided for generating a representation of the reading ability and general knowledge of a user, receiving information regarding a plurality of electronic documents, generating an estimate of the reading difficulty for the user of each electronic document of the plurality of electronic documents using the generated representation of the reading ability and general knowledge of the user, and presenting results based upon the estimates of the reading difficulty. The representation of the reading ability and general knowledge of a user may then be updated based, in part, upon feedback from the user regarding the presented results.

Abstract: A method includes training a neural network having parameters on training data, in which the neural network receives an input state and processes the input state to generate a respective score for each decision in a set of decisions. The method includes receiving training data including training text sequences and, for each training text sequence, a corresponding gold decision sequence. The method includes training the neural network on the training data to determine trained values of parameters of the neural network. Training the neural network includes for each training text sequence: maintaining a beam of candidate decision sequences for the training text sequence, updating each candidate decision sequence by adding one decision at a time, determining that a gold candidate decision sequence matching a prefix of the gold decision sequence has dropped out of the beam, and in response, performing an iteration of gradient descent to optimize an objective function.

Abstract: A system and associated methods are provided for generating a representation of the reading ability and general knowledge of a user, receiving information regarding a plurality of electronic documents, generating an estimate of the reading difficulty for the user of each electronic document of the plurality of electronic documents using the generated representation of the reading ability and general knowledge of the user, and presenting results based upon the estimates of the reading difficulty. The representation of the reading ability and general knowledge of a user may then be updated based, in part, upon feedback from the user regarding the presented results.