There has been great progress in improving streaming machine translation, a simultaneous paradigm where the system appends to a growing hypothesis as more source content becomes available. We study a related problem in which revisions to the hypothesis beyond strictly appending words are permitted. This is suitable for applications such as live captioning an audio feed. In this setting, we compare custom streaming approaches to re-translation, a straightforward strategy where each new source token triggers a distinct translation from scratch. We find retranslation to be as good or better than stateof-the-art streaming systems, even when operating under constraints that allow very few revisions. We attribute much of this success to a previously proposed data-augmentation technique that adds prefix-pairs to the training data, which alongside wait-k inference forms a strong baseline for streaming translation. We also highlight re-translation's ability to wrap arbitrarily powerful MT systems with an experiment showing large improvements from an upgrade to its base model.

Directly in the thermodynamic limit, we show how to combine local imaginary and real-time evolution of tensor networks to efficiently and accurately find the nonequilibrium steady states (NESSs) of one-dimensional dissipative quantum lattices governed by a local Lindblad master equation. The imaginary time evolution first bypasses any highly correlated portions of the real-time evolution trajectory by directly converging to the weakly correlated subspace of the NESS, after which, real-time evolution completes the convergence to the NESS with high accuracy. We demonstrate the power of the method with the dissipative transverse field quantum Ising chain. We show that a crossover of an order parameter shown to be smooth in previous finite-size studies remains smooth in the thermodynamic limit.

Neural Machine Translation (NMT) models have demonstrated strong state of the art performance on translation tasks where well-formed training and evaluation data are provided, but they remain sensitive to inputs that include errors of various types. Specifically, in the context of long-form speech translation systems, where the input transcripts come from Automatic Speech Recognition (ASR), the NMT models have to handle errors including phoneme substitutions, grammatical structure, and sentence boundaries, all of which pose challenges to NMT robustness. Through in-depth error analysis, we show that sentence boundary segmentation has the largest impact on quality, and we develop a simple data augmentation strategy to improve segmentation robustness.

Modern data center solid state drives (SSDs) integrate multiple general-purpose embedded cores to manage ash translation layer, garbage collection, wear-leveling, and etc., to improve the performance and the reliability of SSDs. As the performance of these cores steadily improves there are opportunities to repurpose these cores to perform application driven computations on stored data, with the aim of reducing the communication between the host processor and the SSD. Reducing host-SSD bandwidth demand cuts down the I/O time which is a bottleneck for many applications operating on large data sets. However, the embedded core performance is still signicantly lower than the host processor, as generally wimpy embedded cores are used within SSD for cost eective reasons. So there is a trade-o between the computation overhead associated with near SSD processing and the reduction in communication overhead to the host system. In this work, we design a set of application programming interfaces (APIs) that can be used by the host application to ooad a data intensive task to the SSD processor. We describe how these APIs can be implemented by simple modications to the existing Non-Volatile Memory Express (NVMe) command interface between the host and the SSD processor. We then quantify the computation versus communication tradeos for near storage computing using applications from two important domains, namely data analytics and data integration. Using a fully functional SSD evaluation platform we perform design space exploration of our proposed approach by varying the bandwidth and computation capabilities of the SSD processor. We evaluate static and dynamic approaches for dividing the work between the host and SSD processor, and ⇤ Gunjae and Kiran contributed equally to the paper.