Generative image editing using diffusion models has become a prevalent application in today's AI cloud services. In production environments, image editing typically involves a mask that specifies the regions of an image template to be edited. The use of mask provides direct control over the editing process and introduces sparsity in the model inference. In this paper, we present FlashPS, a system that efficiently serves image editing requests. The key insight behind FlashPS is that image editing only modifies the masked regions of image templates, while preserving the original content in the unmasked areas. Driven by this insight, FlashPS judiciously skips redundant computations associated with the unmask areas by reusing cached intermediate activations from previous inferences. To mitigate the high cache loading overhead, FlashPS employs a bubble-free pipeline scheme that overlaps computation with cache loading. Additionally, to reduce queuing latency in online serving while improving the GPU utilization, FlashPS proposes a novel continuous batching strategy for diffusion model serving, allowing newly arrived requests to join the running batch in just one step of denoising computation, without waiting for the entire batch to complete. As heterogenous masks induce imbalanced load, FlashPS also develops a load balancing strategy that takes into account the loads of both computation and cache loading. Collectively, FlashPS outperforms state-of-the-art diffusion serving systems for image editing, achieving up to 3× higher throughput and reducing average request latency by up to 14.7× while ensuring image quality.

Spoken language understanding (SLU) is the task of inferring the semantics of spoken utterances. Traditionally, this has been achieved with a cascading combination of Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) modules that are optimized separately, which can lead to a suboptimal overall performance. More recently, End-to-End SLU (E2E SLU) was proposed to perform SLU directly from speech through a joint optimization of the modules, addressing some of the traditional SLU shortcomings. A key challenge of this approach is how to best integrate the feature learning of the ASR and NLU sub-tasks to maximize their performance. While it is known that in general, ASR models focus on low-level features, and NLU models need higher-level contextual information, ASR models can nonetheless also leverage top-down syntactic and semantic information to improve their recognition. Based on this insight, we propose Top-Down SLU (TD-SLU), a new transformer-based E2E SLU model that uses top-down attention and an attention gate to fuse high-level NLU features with low-level ASR features, which leads to a better optimization of both tasks. We have validated our model using the public FluentSpeech set, and a large custom dataset. Results show TD-SLU is able to outperform selected baselines both in terms of ASR and NLU quality metrics, and suggest that the added syntactic and semantic high-level information can improve the model’s performance.

While systems using the Neural Network-based Machine Translation (NMT) paradigm achieve the highest scores on recent shared tasks, phrase-based (PBMT) systems, rule-based (RBMT) systems and other systems may get better results for individual examples. Therefore, combined systems should achieve the best results for MT, particularly if the system combination method can take advantage of the strengths of each paradigm. In this paper, we describe a system that predicts whether a NMT, PBMT or RBMT will get the best Spanish translation result for a particular English sentence in DGT-TM 20161. Then we use fuzzy-match repair (FMR) as a mechanism to show that the combined system outperforms individual systems in a black-box machine translation setting.

Event detection (ED) and word sense disambiguation (WSD) are two similar tasks in that they both involve identifying the classes (i.e.event types or word senses) of some word in a given sentence.It is thus possible to extract the knowledge hidden in the data for WSD, and utilize it to improve the performance on ED.In this work, we propose a method to transfer the knowledge learned on WSD to ED by matching the neural representations learned for the two tasks.Our experiments on two widely used datasets for ED demonstrate the effectiveness of the proposed method.