Abstract: Desired vehicle destinations may be determined from spoken dialogs. A speech input may be received from a user through a voice user interface. Current utterance variables may be obtained by tokenizing the user speech input. One or more of a plurality of utterance templates for a reply to the user speech input may be determined by a trained automatic agent based on the plurality of current utterance variables. One of a plurality of Application Programming Interfaces (API) to call and one or more parameters for the API to call with may be determine by the trained automatic agent based on the plurality of current utterance variables. A response may be obtained from the API call. A context string for the reply to the user speech input by the trained automatic agent may be constructed based on the utterance templates and the response of the API call.

Abstract: Sentence pairs can be filtered using dual monolingual conditional cross-entropy filtering. The filtered sentence pairs can be used to train a model for performing a language processing task, such as machine translation.

Abstract: A method may comprise obtaining a machine-learning output generated by a computer system running a trained machine-learning model; obtaining characteristics associated with the generation of the output, the characteristics comprising at least one of an energy term or a power term; determining a precision term for the system based on a comparison of the output with a reference; and determining an overall score of the system based on the precision term and the characteristics.

Abstract: Sentence pairs can be filtered using dual monolingual cross-entropy-delta filtering. The filtered sentence pairs can be used to train a model for performing a language processing task, such as machine translation.

Abstract: Desired vehicle destinations may be determined from spoken dialogs. A speech input may be received from a user through a voice user interface. Current utterance variables may be obtained by tokenizing the user speech input. One or more of a plurality of utterance templates for a reply to the user speech input may be determined by a trained automatic agent based on the plurality of current utterance variables. One of a plurality of Application Programming Interfaces (API) to call and one or more parameters for the API to call with may be determine by the trained automatic agent based on the plurality of current utterance variables. A response may be obtained from the API call. A context string for the reply to the user speech input by the trained automatic agent may be constructed based on the utterance templates and the response of the API call.

Abstract: Sentence pairs can be filtered using dual monolingual conditional cross-entropy filtering. The filtered sentence pairs can be used to train a model for performing a language processing task, such as machine translation.

Abstract: Sentence pairs can be filtered using dual monolingual cross-entropy-delta filtering. The filtered sentence pairs can be used to train a model for performing a language processing task, such as machine translation.

Abstract: An architecture is discussed that provides the capability to subselect the most relevant data from an out-domain corpus to use either in isolation or in combination conjunction with in-domain data. The architecture is a domain adaptation for machine translation that selects the most relevant sentences from a larger general-domain corpus of parallel translated sentences. The methods for selecting the data include monolingual cross-entropy measure, monolingual cross-entropy difference, bilingual cross entropy, and bilingual cross-entropy difference. A translation model is trained on both the in-domain data and an out-domain subset, and the models can be interpolated together to boost performance on in-domain translation tasks.

Abstract: Architecture that provides the capability to subselect the most relevant data from an out-domain corpus to use either in isolation or in combination conjunction with in-domain data. The architecture is a domain adaptation for machine translation that selects the most relevant sentences from a larger general-domain corpus of parallel translated sentences. The methods for selecting the data include monolingual cross-entropy measure, monolingual cross-entropy difference, bilingual cross entropy, and bilingual cross-entropy difference. A translation model is trained on both the in-domain data and an out-domain subset, and the models can be interpolated together to boost performance on in-domain translation tasks.