Abstract: Implementations disclose utilizing a less computationally efficient decoding method in automatically generating corresponding single generative content predictions for training instances and fine-tuning a student generative model based on those automatically generated training instances. Those implementations are further directed to then utilizing, in an inference time environment, the fine-tuned student generative model and a more computationally efficient decoding method in generating generative predictions—and without any utilization of the less computationally efficient decoding method in generating the generative predictions.

Abstract: Techniques are disclosed for training and/or utilizing an automatic post-editing model in correcting translation error(s) introduced by a neural machine translation model. The automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

Abstract: Techniques are disclosed for training and/or utilizing an alignments and language model (“ALM”) in automatically determining an ALM score corresponding with natural language text generated using a natural language generation model. The natural language text generated using the natural language generation model can be based on a set of structured data. Additionally or alternatively, the ALM can include a fluency model portion and a semantics model portion. The fluency model portion can be used in determining the fluency and/or grammar of the text. The semantics model portion be used in evaluating the content of the natural language text with respect to the content of the structured data.

Abstract: Techniques are disclosed for training and/or utilizing an automatic post-editing model in correcting translation error(s) introduced by a neural machine translation model. The automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

Abstract: Provided are systems and methods for sequence-to-sequence modeling with neural quality metrics. More particularly, example aspects of the present disclosure relate to minimum bayes risk (MBR) decoding with neural metrics for machine translation. According to example aspects of the present disclosure, a set of candidate outputs can be sampled from a machine translation model given a source sequence. Given the set of candidate outputs, systems and methods according to example aspects of the present disclosure can select a hypothesis with high expected utility with respect to the distribution over a set of pseudo-references from the machine translation model.

Abstract: Techniques are disclosed for training and/or utilizing an alignments and language model (“ALM”) in automatically determining an ALM score corresponding with natural language text generated using a natural language generation model. The natural language text generated using the natural language generation model can be based on a set of structured data. Additionally or alternatively, the ALM can include a fluency model portion and a semantics model portion. The fluency model portion can be used in determining the fluency and/or grammar of the text. The semantics model portion be used in evaluating the content of the natural language text with respect to the content of the structured data.

Abstract: Techniques are disclosed for training and/or utilizing an automatic post-editing model in correcting translation error(s) introduced by a neural machine translation model. The automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

Abstract: Techniques are disclosed for training and/or utilizing an automatic post-editing model in correcting translation error(s) introduced by a neural machine translation model. The automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

Abstract: Techniques are disclosed for training and/or utilizing an automatic post-editing model in correcting translation error(s) introduced by a neural machine translation model. The automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.