www.amazon.science Open in urlscan Pro
13.224.189.45  Public Scan

Form analysis
1 forms found in the DOM

https://www.amazon.science/search#nt=navsearch

<form class="SearchOverlay-form" action="https://www.amazon.science/search#nt=navsearch" novalidate="" autocomplete="off">
  <button type="submit" class="SearchOverlay-button-submit" aria-label="Search">
    <svg class="icon-magnify">
      <use xlink:href="#icon-magnify"></use>
    </svg>
  </button>
  <label class="sr-only" for="SearchOverlayInput">Search</label>
  <input id="SearchOverlayInput" type="text" class="SearchOverlay-input" name="q" placeholder="Search">
  <button type="button" class="SearchOverlay-button-close Page-header-search-close close"><svg>
      <use xlink:href="#icon-close"></use>
    </svg><span class="sr-only">Submit Search</span></button>
</form>

Text Content

Close Close
 * Research areas
   
    * Automated reasoning
    * Cloud and systems
    * Computer vision
    * Conversational AI / Natural-language processing
    * Economics
    * Information and knowledge management
    * Machine learning
    * Operations research and optimization
    * Quantum technologies
    * Robotics
    * Search and information retrieval
    * Security, privacy, and abuse prevention
    * Sustainability
   
    * Automated reasoning
    * Cloud and systems
    * Computer vision
    * Conversational AI / Natural-language processing
    * Economics
    * Information and knowledge management
    * Machine learning
    * Operations research and optimization
    * Quantum technologies
    * Robotics
    * Search and information retrieval
    * Security, privacy, and abuse prevention
    * Sustainability

 * Blog
 * News and features
   
    * Awards and recognitions
   
    * Awards and recognitions

 * Publications
 * Conferences
 * Collaborations
   
    * Academics at Amazon
    * Alexa Prize
    * Amazon Research Awards
    * Amazon SURE
   
    * Academics at Amazon
    * Alexa Prize
    * Amazon Research Awards
    * Amazon SURE

 * Careers
   
    * Internships
    * Working at Amazon
   
    * Internships
    * Working at Amazon

Subscribe
Follow Us
 * twitter
 * instagram
 * youtube
 * facebook
 * linkedin

Menu

 * Research areas
   
    * Automated reasoning
    * Cloud and systems
    * Computer vision
    * Conversational AI / Natural-language processing
    * Economics
    * Information and knowledge management
    * Machine learning
    * Operations research and optimization
    * Quantum technologies
    * Robotics
    * Search and information retrieval
    * Security, privacy, and abuse prevention
    * Sustainability
   
    * Automated reasoning
    * Cloud and systems
    * Computer vision
    * Conversational AI / Natural-language processing
    * Economics
    * Information and knowledge management
    * Machine learning
    * Operations research and optimization
    * Quantum technologies
    * Robotics
    * Search and information retrieval
    * Security, privacy, and abuse prevention
    * Sustainability

 * Blog
 * News and features
   
    * Awards and recognitions
   
    * Awards and recognitions

 * Publications
 * Conferences
 * Collaborations
   
    * Academics at Amazon
    * Alexa Prize
    * Amazon Research Awards
    * Amazon SURE
   
    * Academics at Amazon
    * Alexa Prize
    * Amazon Research Awards
    * Amazon SURE

 * Careers
   
    * Internships
    * Working at Amazon
   
    * Internships
    * Working at Amazon


Subscribe
Search Submit Search



CUSTOMER-OBSESSED SCIENCE




FROM THE BLOG

View all
The latest research from Amazon scientists.
View all
 * Lessons learned from 10 years of DynamoDB
   October 21, 2022
   Prioritizing predictability over efficiency, adapting data partitioning to
   traffic, and continuous verification are a few of the principles that help
   ensure stability, availability, and efficiency.
   Cloud and systems
 * Maximizing the efficiency of Amazon's own delivery networks
   October 14, 2022
   INFORMS talk explores techniques Amazon’s Supply Chain Optimization
   Technologies organization is testing to fulfill customer orders more
   efficiently.
   Operations research and optimization
 * Adapted from a figure by Johan Jarnestad for the Royal Swedish Academy of
   Sciences
   3 questions with Antia Lamas-Linares about the Nobel Prize in physics
   October 12, 2022
   The head of Amazon Web Services’ quantum communication program on the Nobel
   winners’ influence on her field.
   Quantum technologies


 * CONFERENCE CALENDAR
   
    * IROS 2022
      Robotics
      October 23 - 27, 2022
    * ECCV 2022
      Computer vision
      October 23 - 27, 2022
    * NeurIPS 2022
      Machine learning
      November 28 - December 9, 2022


NEWS AND FEATURES

View all
The latest news about scientific innovation at Amazon.
View all
 * Amazon Robotics welcomes students to inaugural Day One Fellowship Summit
   October 25, 2022
   Summit offered Day One fellows the opportunity to interact with leaders in
   the robotics field.
   Robotics
 * The quest to deploy autonomous robots within Amazon fulfillment centers
   October 24, 2022
   Company is testing a new class of robots that use artificial intelligence and
   computer vision to move freely throughout facilities.
   Robotics
 * reMARS revisited: Net zero carbon goal and Amazon’s fulfillment network
   October 18, 2022
   Examining the opportunities for reducing energy consumption in robotics and
   automation across Amazon's fulfillment center network.
   Sustainability
 * reMARS revisited: Amazon’s supply chain optimization
   October 18, 2022
   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.
   Operations research and optimization


RECENT PUBLICATIONS

View all View all
 * Memory efficient continual learning with transformers
   Beyza Ermis, Giovanni Zappella, Martin Wistuba, Cedric Archambeau
   NeurIPS 2022
   2022
   In many real-world scenarios, data to train machine learning models becomes
   available over time. Unfortunately, these models struggle to continually
   learn new concepts without forgetting what has been learnt in the past. This
   phenomenon is known as catastrophic forgetting and it is difficult to prevent
   due to practical constraints. For instance, the… Read More
   Conversational AI / Natural-language processing
 * Distilling multilingual transformers into CNNs for scalable intent
   classification
   Besnik Fetahu, Akash Veeragouni, Oleg Rokhlenko, Shervin Malmasi
   EMNLP 2022
   2022
   We describe an application of Knowledge Distillation used to distill and
   deploy multilingual Transformer models for voice assistants, enabling text
   classification for customers globally. Transformers have set new
   state-of-theart results for tasks like intent classification, and
   multilingual models exploit cross-lingual transfer to allow serving requests
   across… Read More
   Conversational AI / Natural-language processing
 * Cross-lingual transfer for low-resource Arabic language understanding
   Khadige Abboud, Olga Golovneva, Christopher DiPersio
   EMNLP 2022 Workshop on Arabic Natural Language Processing (WANLP)
   2022
   This paper explores cross-lingual transfer learning in natural language
   understanding (NLU), with the focus on bootstrapping Arabic from
   high-resource English and French languages for domain classification, intent
   classification, and named entity recognition tasks. We adopt a BERT-based
   architecture and pretrain three models using open-… Read More
   Conversational AI / Natural-language processing
 * Are abstractive summarization models truly ‘abstractive’? An empirical study
   to compare the two forms of summarization
   Vinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah
   EMNLP 2022 Workshop on Generation, Evaluation & Metrics (GEM)
   2022
   Automatic Text Summarization has seen a large paradigm shift from extractive
   methods to abstractive (or generation-based) methods in the last few years.
   This can be attributed to the availability of large autoregressive language
   models (Lewis et al., 2019; Zhang et al., 2019a) that have been shown to
   outperform extractive methods. In this… Read More
   Conversational AI / Natural-language processing
 * Context-situated pun generation
   Jiao Sun, Anjali Narayan-Chen, Shereen Oraby, Shuyang Gao, Tagyoung Chung,
   Jing Huang, Yang Liu, Nanyun Peng
   EMNLP 2022
   2022
   Previous work on pun generation commonly begins with a given pun word (a pair
   of homophones for heterographic pun generation and a polyseme for homographic
   pun generation) and seeks to generate an appropriate pun. While this may
   enable efficient pun generation, we believe that a pun is most entertaining
   if it fits appropriately within a… Read More
   Conversational AI / Natural-language processing

Load More


COLLABORATIONS

View all
Amazon engages with the science community in a number of ways.
View all
 * Amazon Research Awards recipients announced
   October 10, 2022
   Awardees represent more than 30 universities in eight countries. Recipients
   have access to Amazon public datasets, along with AWS AI/ML services and
   tools.
 * Amazon launches Alexa Prize TaskBot Challenge 2
   September 22, 2022
   University teams are invited to compete to build multimodal conversational
   agents that assist customers in completing tasks requiring multiple steps.
   Conversational AI / Natural-language processing
 * Amazon Research Awards issues fall 2022 call for proposals
   September 16, 2022
   The submission period deadline has been extended to October 26.


WORKING AT AMAZON

View all
Meet the people driving the innovation essential to being the world’s most
customer-centric company.
View all
 * “I always knew that my main interest was in supply chain optimization”
   August 29, 2022
   After 15 years in academia, Alp Muharremoglu became a senior principal
   scientist within Amazon’s Supply Chain Optimization Technologies
   organization, and says his teaching skills are indispensable.
   Operations research and optimization
 * Using data science to help improve NFL quarterback passing scores
   August 26, 2022
   Principal data scientist Elena Ehrlich uses her skills to help a wide variety
   of customers — including the National Football League.
   Machine learning
 * Why Amazon Scholar Yossi Keshet remains "excited about speech"
   August 23, 2022
   New speech representations and self-supervised learning are two of the recent
   trends that most intrigue him.
   Conversational AI / Natural-language processing


WORK WITH US

See more jobs See more jobs
Applied Scientist - NLP
US, WA, Seattle
Job summaryDo you want the excitement of experimenting with cutting edge machine
learning, natural language processing,… Read More
Data Scientist, Infra Supply Chain Automation
US, VA, Arlington
Job summaryWe are looking for a highly motivated, analytical and detail-oriented
candidate to help build scalable prescriptive… Read More
Data Scientist, Advertising Catalyst
US, NY, New York
Job summaryAmazon Advertising is one of Amazon's fastest growing and most
profitable businesses, responsible for… Read More
Amazon Robotics - Research Scientist Intern - Summer 2023
US, MA, North Reading
Job summaryAre you inspired by invention? Is problem solving through teamwork in
your DNA? Do you like the idea of seeing how your work… Read More
Data Scientist
US, VA, Arlington
Job summaryAmazon Advertising is one of Amazon's fastest growing and most
profitable businesses, responsible for… Read More
Applied Scientist, Core AI
US, WA, Seattle
Job summaryThe Core AI team uses Machine Learning, Economics, Statistics to
understand and design the complex economy… Read More
Data Scientist, DISCO
US, GA, Atlanta
Job summaryAt Amazon Music we are creating an immersive audio-first
entertainment service spanning music and spoken world that… Read More
Data Science Manager
PL, Gdansk
Job summary Join our growing team of software engineers and predictive modelers
that are building best-in-class tools and large-scale… Read More
Applied Scientist II - AMZ5912598
US, MN, Minneapolis
Job summaryMULTIPLE POSITIONS AVAILABLECompany: AMAZON DEV CENTER U.S.,
INC.Position Title: Applied… Read More
Senior Data Scientist for AWS Worldwide Specialist Organization (WWSO), AWS
Finance, Analytics and Science Team
US, WA, Seattle
Job summaryThis role can be based in Seattle, WA, Herndon, VA, Jersey City, NJ,
Culver City, CA, or San Francisco, CA,.Join the Amazon Web… Read More
 * About
 * Research areas
 * Blog
 * News and features
 * Publications
 * Conferences
 * Collaborations
 * Careers
 * Alexa Prize
 * Academics
 * Research Awards
 * Amazon Developer
 * Amazon Web Services
 * Newsletter
 * FAQs
 * RSS

Get more from Amazon Science
Sign up for our newsletter
Subscribe
Amazon.com | Conditions of Use | Privacy | © 1996-2022 Amazon.com, Inc. or its
affiliates
Follow Us
 * twitter
 * instagram
 * youtube
 * facebook
 * linkedin