Data mining

Identifying helpful sentences in product reviews

Iftah Gamzu, Hila Gonen, Gilad Kutiel, Ran Levy, Eugene Agichtein

NAACL 2021

2021

In recent years online shopping has gained momentum and became an important venue for customers wishing to save time and simplify their shopping process. A key advantage of shopping online is the ability to read what other customers are saying about products of interest. In this work, we aim to maintain this advantage in situations where extreme brevity is needed, for example, when shopping by voice. We

Machine learning

Christos Faloutsos awarded PAKDD’s “Most Influential Paper Award”

Staff writer

December 18, 2020

Amazon Scholar and Carnegie Mellon professor of artificial intelligence, Christos Faloutsos

Amazon Scholar and Carnegie Mellon professor of artificial intelligence and coauthors honored for paper that proposed a new approach to detecting anomalies in large, weighted graphs.

Information and knowledge management

AWS director of machine learning explains the significance of new Amazon HealthLake service

Staff writer

December 09, 2020

Diagram that describes the features of Amazon HealthLake

Taha Kass-Hout says the service’s secret sauce is its ability to create a comprehensive data set within a secure data lake that can be organized by different attributes, and then queried and analyzed with advanced analytics and machine learning.

Machine learning

Amazon Scholar George Karypis receives ICDM 10-Year-Highest-Impact award

Staff writer

December 08, 2020

University of Minnesota professor and Amazon Scholar, together with coauthor, receives recognition for paper that proposes novel approach to algorithm that generates high-quality recommendations for e-commerce products at high speeds.

Search and information retrieval

What’s mine is yours, what’s yours is mine

Karan Matnani, Valerie Liptak, George Forman

Simplify 2021

2021

At Amazon Last Mile, we deliver over 3.5 billion packages every year, making us one of the largest delivery companies in the world. At this scale, even small changes can have a big business impact. In general, business impact is assessed using controlled experimentation. A standard approach to evaluating whether controlled experiments resulted in a significant change has been to use a t-test. However, despite

Information and knowledge management

Developing machine learning techniques to enrich product-related information from Amazon detail pages and the Internet at large.

Data lake vs. data warehouse: Why AWS customers are transitioning to data lakes

September 10, 2020

Presentation screengrab: The Evolution of Data Warehousing - Data Lakes with AWS Lake Formation

Mehul Shah, GM for AWS Lake Formation and AWS Glue, explains what data lakes are, the challenges of data lakes, and how technology can help.

Information and knowledge management

COVID-19 knowledge graph: Accelerating information retrieval and discovery for scientific literature

Colby Wise, Vassilis N. Ioannidis, Miguel Romero Calvo, Xiang Song, George Price, Ninad Kulkani, Ryan Brand, Parminder Bhatia, George Karypis

AACL-IJCNLP 2020 Workshop on Integrating Structured Knowledge and Neural Networks for NLP (KNLP)

2020

The coronavirus disease (COVID-19) has claimed the lives of over one million people and infected more than thirty-five million people worldwide. Several search engines have surfaced to provide researchers with additional tools to find and retrieve information from the rapidly growing corpora on COVID-19. These engines lack extraction and visualization tools necessary to retrieve and interpret complex relations

Information and knowledge management

Analysis of e-commerce ranking signals via signal temporal logic

Tommaso Dreossi, Giorgio Ballardin, Parth Gupta, Jan Bakus, Yu-Hsiang Lin, Vamsi Salaka

QONFEST 2020

2020

The timed position of documents retrieved by learning to rank models can be seen as signals. Signals carry useful information such as drop or rise of documents over time or user behaviors. In this work, we propose to use the logic formalism called Signal Temporal Logic (STL) to characterize document behaviors in ranking accordingly to the specified formulas. Our analysis shows that interesting document

Computer vision

CorDEL: A contrastive deep learning approach for entity linkage

Zhengyang Wang, Bunyamin Sisman, Hao Wei, Xin Luna Dong, Shuiwang Ji

ICDM 2020

2020

Entity linkage (EL) is a critical problem in data cleaning and integration. In the past several decades, EL has typically been done by rule-based systems or traditional machine learning models with hand-curated features, both of which heavily depend on manual human inputs. With the ever-increasing growth of new data, deep learning (DL) based approaches have been proposed to alleviate the high cost of EL

Information and knowledge management

Data mining

Work with us