Search results

Because of the increasing demand for intensive computation in deep neural networks, researchers have developed both hardware and software mechanisms to reduce the compute and memory burden. A widely adopted approach is to use mixed precision data types. However, it is hard to benefit from mixed precision without hardware specialization because of the overhead of data casting. Recently, hardware vendors

Dialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in ask oriented dialogs. In real-world settings with constantly changing services, DST systems must generalize to new domains and unseen slot types. Existing methods for DST do not generalize well to new slot names and many require known ontologies of slot types and values for inference

Most prior work on task-oriented dialogue systems are restricted to a limited coverage of domain APIs, while users oftentimes have domain related requests that are not covered by the APIs. This challenge track aims to expand the coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources. We define three tasks: knowledge-seeking turn detection, knowledge selection

FreeRTOS is a real-time kernel and set of libraries for Internet of Things (IoT) applications. The FreeRTOS kernel provides a portable abstraction layer, task scheduling and interprocess communication (IPC) mechanisms. The main IPC mechanism in FreeRTOS is a concurrent queue: a circular buffer data structure that tasks and interrupt service routines use to exchange messages. As a fundamental building block

How Amazon is aligning its decarbonization goals with the best available science.

Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to over-smoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of graph heterophily or adversarial attacks. To at least partially address these issues within a simple transparent framework, we consider a new family of GNN layers designed

We present an end-to-end system for learning outfit recommendations. The core problem we address is how a customer can receive clothing/accessory recommendations based on a current outfit and what type of item the customer wishes to add to the outfit. Using a repository of coherent and stylish outfits, we leverage self-attention to learn a mapping from the current outfit and the customer-requested category

In this paper, we explore learning end-to-end deep neural trackers without tracking annotations. This is important as large-scale training data is essential for deep neural trackers, while tracking annotations are expensive to acquire. We first hallucinate videos from images with bounding box annotations using motion transformations along with simulated video effects to create a diverse tracking dataset

Meta-learning learns across historical tasks with the goal to discover a representation from which it is easy to adapt to unseen tasks. Episodic meta-learning attempts to simulate a realistic setting by generating a set of small artificial tasks from a larger set of training tasks for meta-training and proceeds in a similar fashion for meta-testing. However, this (meta-)learning paradigm has recently been

Federated Learning is a distributed learning setting where the goal is to train a centralized model with training data distributed over a large number of heterogeneous clients, each with unreliable and relatively slow network connections. A common optimization approach used in federated learning is based on the idea of local SGD: each client runs some number of SGD steps locally and then the updated local

To improve customer privacy, commercial speech applications are reducing human transcription of customer data. This has a negative impact on language model training due to a smaller amount of in-domain transcripts. Prior work demonstrated that training on automated transcripts alone provides modest gains due to reinforcement of recognition errors. We consider a new condition, where a model trained on historical

Generalization is a central problem in machine learning, especially when data is limited. Using prior information to enforce constraints is the principled way of encouraging generalization. In this work, we propose to leverage the prior information embedded in pretrained language models (LM) to improve generalization for intent classification and slot labeling tasks with limited training data. Specifically

With the expanding role of voice-controlled devices, bootstrapping spoken language understanding models from little labeled data becomes essential. Semi-supervised learning is a common technique to improve model performance when labeled data is scarce. In a real-world production system, the labeled data and the online test data often may come from different distributions. In this work, we use semi-supervised

Meta-learning has recently been proposed to learn models and algorithms that can generalize from a handful of examples. However, applications to structured prediction and textual tasks pose challenges for meta-learning algorithms. In this paper, we apply two metalearning algorithms, Prototypical Networks and Reptile, to few-shot Named Entity recognition (NER), including a method for incorporating language

Bayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods. BO proposes solutions according to an explore-exploit trade-off criterion encoded in an acquisition function, many of which are computed from the posterior predictive of a probabilistic surrogate model. Prevalent among these is the expected improvement (EI). The need to ensure analytical tractability of

Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker. While there is a rich literature on VC, most proposed methods are trained and evaluated on clean speech recordings. However, many acoustic environments are noisy and reverberant, severely restricting the applicability of popular VC methods to such