Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.

Abstract: Methods and apparatus related to determining a semantically diverse subset of candidate responses to provide for initial presentation to a user as suggestions for inclusion in a reply to an electronic communication. Some of those implementations determine the semantically diverse subset of candidate responses based on generating, over a neural network response encoder model, embeddings that are each based on one of the plurality of the candidate responses. The embedding based on a given candidate response may be compared to embedding(s) of candidate response(s) already selected for the subset, and the given candidate response added to the subset only if the comparing indicates a difference criterion is satisfied.

Abstract: Methods and apparatus related to determining a semantically diverse subset of candidate responses to provide for initial presentation to a user as suggestions for inclusion in a reply to an electronic communication. Some of those implementations determine the semantically diverse subset of candidate responses based on generating, over a neural network response encoder model, embeddings that are each based on one of the plurality of the candidate responses. The embedding based on a given candidate response may be compared to embedding(s) of candidate response(s) already selected for the subset, and the given candidate response added to the subset only if the comparing indicates a difference criterion is satisfied.

Abstract: To reduce our carbon footprint on the planet, there needs to be better systems and methods of coordinating travel among people. The presently disclosed system not only allows for ride sharing to take place, the driver can also be rewarded with financial incentives while the passenger not only is able to get to the desired destination, he or she can also save money by not having to maintain a vehicle, not to mention numerous other benefits to the environment and society.