Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.
-
June 28, 2023Four CVPR papers from Prime Video examine a broad set of topics related to efficient model training for understanding and synthesizing long-form cinematic content. -
June 20, 2023Image segmentation, multimodal models, and innovative machine learning methods are among the Amazon researchers' areas of focus. -
June 20, 2023SIGMOD paper by Amazon researchers and collaborators presents flexible data definition language that enables rapid development of complex graph databases. -
-
July 9 - 14, 2023
-
July 17 - 22, 2023
-
July 24 - 29, 2023
-
-
June 28, 2023Ongoing collaboration includes Amazon joining the UW Center for the Future of Cloud Infrastructure. -
June 27, 2023Two Max Planck Society researchers receive funding for projects to develop new ways to advance a more circular economy. -
June 26, 2023How phonetically blended results (PBR) help ensure customers find the content they were actually asking for. -
June 22, 2023Kanoria and coauthors honored for their paper narrowing the gap between theoretical understanding and practical experience in matching markets.
-
2023Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have been recently developed for refining the ASR outputs. However, efficient models that meet the low latency requirements of industrial grade production systems have not been well studied. We propose PATCorrect-a novel non-autoregressive
-
2023User Satisfaction Modeling (USM) is one of the popular choices for task-oriented dialogue systems evaluation, where user satisfaction typ-ically depends on whether the user’s task goals were fulfilled by the system. Task-oriented dialogue systems use task schema, which is a set of task attributes, to encode the user’s task goals. Existing studies on USM neglect explicitly modeling the user’s task goals
-
2023Policy Optimization (PO) is one of the most popular methods in Reinforcement Learning (RL). Thus, theoretical guarantees for PO algorithms have become especially important to the RL community. In this paper, we study PO in adversarial MDPs with a challenge that arises in almost every real-world application – delayed bandit feedback. We give the first near-optimal regret bounds for PO in tabular MDPs, and
-
ACL 2023 Workshop on Lexical and Computational Semantics and Semantic Evaluation2023We present the findings of SemEval-2023 Task 2 on Fine-grained Multilingual Named Entity Recognition (MULTICONER 2).1 Divided into 13 tracks, the task focused on methods to identify complex fine-grained named entities (like WRITTENWORK, VEHICLE, MUSICALGRP) across 12 languages, in both monolingual and multilingual scenarios, as well as noisy settings. The task used the MULTICONER V2 dataset, composed of
-
STOC 20232023We consider the problem of online service with delay on a general metric space, first presented by Azar, Ganesh, Ge and Panigrahi (STOC 2017). The best known randomized algorithm for this prob-lem, by Azar and Touitou (FOCS 2019), is 𝑂 (log2 𝑛)-competitive, where 𝑛 is the number of points in the metric space. This is also the best known result for the special case of online service with deadlines, which
-
June 29, 2023University teams are invited to compete to build multimodal conversational agents that assist customers in completing tasks requiring multiple steps. -
June 07, 2023Team earned $500,000 for its performance in a challenge focused on advancing next-generation virtual assistants that help humans complete real-world tasks by continuously learning. -
May 24, 2023How ARA recipient Supreeth Shashikumar is using machine learning to help hospitals detect sepsis — before it’s too late.
Working at Amazon
View allMeet the people driving the innovation essential to being the world’s most customer-centric company.
View all
-
June 21, 2023The senior applied science manager envisions machine learning as the path to a better experience for Amazon customers. -
April 05, 2023As a senior principal applied scientist at Amazon Web Services, Leino is continuing his career as a leading expert in program verification. -
March 14, 2023Ren Zhang and her team tackle the interesting science challenges behind surfacing the most relevant offerings.
