Search Amazon Science for the latest news, articles, blog posts, publications, conferences and events. You can filter search results by research area, date and content type.
Static Analysis tools have rules for several code quality issues and these rules are created by experts manually. In this paper, we address the problem of automatic synthesis of code quality rules from examples. We formulate the rule synthesis problem as synthesizing first order logic formulas over…
We introduce a general framework for nonlinear stochastic gradient descent (SGD) for the scenarios when gradient noise exhibits heavy tails. The proposed framework subsumes several popular nonlinearity choices, like clipped, normalized, signed or quantized gradient, but we also consider novel…
With ever-growing digital adoption in the society and increasing demand for businesses to deliver to customers doorstep, the last mile hop of transportation planning poses unique challenges in emerging geographies with unstructured addresses. One of the crucial inputs to facilitate effective…
Although the variational autoencoder (VAE) and its conditional extension (CVAE) are capable of state-of-the-art results across multiple domains, their precise behavior is still not fully understood, particularly in the context of data (like images) that lie on or near a low-dimensional manifold.…
The fundamental challenge of drawing causal inference is that counterfactual outcomes are not fully observed for any unit. Furthermore, in observational studies, treatment assignment is likely to be confounded. Many statistical methods have emerged for causal inference under unconfoundedness…
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. The conference is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition
Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design decision assumes the primary input data source does not change and if an additional (auxiliary) data source is…
Amazon is proud to sponsor the 2022 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT 2022).
Increasing concerns and regulations about data privacy and sparsity necessitate the study of privacy-preserving, decentralized learning methods for natural language processing (NLP) tasks. Federated learning (FL) provides promising approaches for a large number of clients (e.g., personal devices or…
We present a very simple method for extending pretrained machine translation metrics to incorporate document-level context. We apply our method to four popular metrics: BERTScore, Prism, COMET, and the reference-free metric COMET-QE. We evaluate our document-level metrics on the MQM annotations…
Hyperparameter optimization (HPO) and neural architecture search (NAS) are methods of choice to obtain the best-in-class machine learning models, but in practice they can be costly to run. When models are trained on large datasets, tuning them with HPO or NAS rapidly becomes prohibitively expensive…
Modern recommender systems are often modelled under the sequential decision-making paradigm, where the system decides which recommendations to show in order to maximise some notion of either imminent or long-term reward. Such methods often require an explicit model of the reward a certain…
In the last several years, end-to-end (E2E) ASR models have mostly surpassed the performance of hybrid ASR models. E2E is particularly well suited to multilingual approaches because it doesn’t require language-specific phone alignments for training. Recent work has improved multilingual E2E…
Previous work suggests that performance of cross-lingual information retrieval correlates highly with the quality of Machine Translation. However, there may be a threshold beyond which improving query translation quality yields little or no benefit to further improve the retrieval performance. This…
Open world classification is a task in natural language processing with key practical relevance and impact. Since the open or unknown category data only manifests in the inference phase, finding a model with a suitable decision boundary accommodating for the identification of known classes and…
How the SCOT team implemented a system that leverages operations research and machine learning to decide what products to buy, how much to buy, where to place them, and more.