Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...Rakuten Group, Inc.
The document proposes a knowledge-driven query expansion approach for question answering (QA)-based product attribute extraction. It trains QA models using attribute-value pairs from training data as knowledge, while mimicking imperfect knowledge at test time through techniques like knowledge dropout and token mixing. This helps induce better query representations, especially for rare and ambiguous attributes. Experiments on a cleaned product attribute dataset show the proposed approach with all techniques outperforms baseline methods in both macro and micro F1 scores.
This document provides an overview of a QA Night event hosted by Rakuten's Service Quality Assurance Group. It includes an introduction to the event as well as an agenda with times and speakers. The agenda focuses on utilizing data from the software testing life cycle (STLC) for various purposes like process improvement, automation frameworks, and reporting to stakeholders. Speakers will provide case studies and examples of how they apply STLC data. The event aims to discuss best practices for collecting, utilizing, and improving the use of testing data throughout the software development life cycle at Rakuten.
2019年07月09日 リカレントエデュケーション講座@京橋。
楽天ではどのようにビッグデータを活用しているのか、データサイエンス&AIの最新応用事例の紹介。
およびデータサイエンス系のプロジェクトの進め方と,必要な役割についての紹介。
登壇者:平手勇宇(Rakuten Institute of Technology Tokyo)
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...Rakuten Group, Inc.
The document proposes a knowledge-driven query expansion approach for question answering (QA)-based product attribute extraction. It trains QA models using attribute-value pairs from training data as knowledge, while mimicking imperfect knowledge at test time through techniques like knowledge dropout and token mixing. This helps induce better query representations, especially for rare and ambiguous attributes. Experiments on a cleaned product attribute dataset show the proposed approach with all techniques outperforms baseline methods in both macro and micro F1 scores.
This document provides an overview of a QA Night event hosted by Rakuten's Service Quality Assurance Group. It includes an introduction to the event as well as an agenda with times and speakers. The agenda focuses on utilizing data from the software testing life cycle (STLC) for various purposes like process improvement, automation frameworks, and reporting to stakeholders. Speakers will provide case studies and examples of how they apply STLC data. The event aims to discuss best practices for collecting, utilizing, and improving the use of testing data throughout the software development life cycle at Rakuten.
2019年07月09日 リカレントエデュケーション講座@京橋。
楽天ではどのようにビッグデータを活用しているのか、データサイエンス&AIの最新応用事例の紹介。
およびデータサイエンス系のプロジェクトの進め方と,必要な役割についての紹介。
登壇者:平手勇宇(Rakuten Institute of Technology Tokyo)
This document provides an overview of the selfree LLC company. It discusses the company's founding in 2014, its mission to increase loved companies, its 3 employees and services including CallConnect and wellcast. It describes the company's flat structure, remote work environment, benefits like an office in Narusawa with onsen access, and culture of transparency, autonomy, efficiency and work-life balance. The summary seeks to highlight key details about the company's profile, services, work environment and culture.
The document summarizes a presentation by Itakawa Ichigaku on using machine learning and optimal experimental design for heterogeneous catalysis research. Itakawa introduces himself and his background working in machine learning and its applications in natural science fields. He emphasizes that applying machine learning to natural sciences requires close collaboration with domain experts and understanding ML's capabilities and limitations. The presentation aims to help audiences understand these points and properly position ML's role in exploratory research through examples from his past work.
Bessemer Venture Partners' is proud to share The State of the Cloud for 2017.
As the definitive guide to the biggest trends in the cloud industry, this year’s “State of the Cloud Report” includes:
1. A Look Back at 2016
- 2016 was a marquee year for a number of reasons. First, we all remember the rocky start in February where the Cloud Market dropped 35%
- Subsequently, rebounded back to normal levels and ended the year up +15%.
- The dip in the market had two main outcomes: First, it led to unprecedented amounts of M&A (4x more than any other year and 40% of the total cloud market cap of $300B) – and second, it led to the fewest number of cloud tech IPOs since the financial crisis.
- A combination of these factors has led to the highest quality backlog of private cloud companies in history. The top 100 private Cloud companies alone represent over $100B of private enterprise value.
2. We provide a deeper look into the three top questions every private cloud CEO should be discussing with his/her executive team
- How fast should I be growing?
- How much should I burn?
- How do I scale?
3. Bessemer’s 7 Predictions for 2017
- The year of human assisted AI
- APIs will serve as the backbone for a majority of software infrastructure
- Architect for infinite scale without infinite spend
- Mobile unlocks non-desk worker productivity
- NPS everything
- Diverse teams win
- The screenless software movement
This document provides an overview of the selfree LLC company. It discusses the company's founding in 2014, its mission to increase loved companies, its 3 employees and services including CallConnect and wellcast. It describes the company's flat structure, remote work environment, benefits like an office in Narusawa with onsen access, and culture of transparency, autonomy, efficiency and work-life balance. The summary seeks to highlight key details about the company's profile, services, work environment and culture.
The document summarizes a presentation by Itakawa Ichigaku on using machine learning and optimal experimental design for heterogeneous catalysis research. Itakawa introduces himself and his background working in machine learning and its applications in natural science fields. He emphasizes that applying machine learning to natural sciences requires close collaboration with domain experts and understanding ML's capabilities and limitations. The presentation aims to help audiences understand these points and properly position ML's role in exploratory research through examples from his past work.
Bessemer Venture Partners' is proud to share The State of the Cloud for 2017.
As the definitive guide to the biggest trends in the cloud industry, this year’s “State of the Cloud Report” includes:
1. A Look Back at 2016
- 2016 was a marquee year for a number of reasons. First, we all remember the rocky start in February where the Cloud Market dropped 35%
- Subsequently, rebounded back to normal levels and ended the year up +15%.
- The dip in the market had two main outcomes: First, it led to unprecedented amounts of M&A (4x more than any other year and 40% of the total cloud market cap of $300B) – and second, it led to the fewest number of cloud tech IPOs since the financial crisis.
- A combination of these factors has led to the highest quality backlog of private cloud companies in history. The top 100 private Cloud companies alone represent over $100B of private enterprise value.
2. We provide a deeper look into the three top questions every private cloud CEO should be discussing with his/her executive team
- How fast should I be growing?
- How much should I burn?
- How do I scale?
3. Bessemer’s 7 Predictions for 2017
- The year of human assisted AI
- APIs will serve as the backbone for a majority of software infrastructure
- Architect for infinite scale without infinite spend
- Mobile unlocks non-desk worker productivity
- NPS everything
- Diverse teams win
- The screenless software movement
This document discusses how to make software more green and environmentally friendly. It defines green software as software that is carbon efficient, energy efficient, hardware efficient, and carbon aware. It provides recommendations for various roles within an organization on driving green initiatives, including focusing on efficiency for CxOs, architects, infrastructure engineers, and developers. Examples include optimizing resource usage, using public clouds effectively, prioritizing equipment standardization, and developing applications that can run more efficiently.
This document summarizes Andrew Hajinikitas' work developing Rakuten's private cloud infrastructure. It describes the key components of Rakuten's infrastructure including metal instances, microservers, and GPU servers. It provides details on Rakuten's software stack and their goals to expand managed services. Currently, Rakuten operates 9 data centers in Japan and overseas providing around 30,000 servers to support their ecosystem. Their future plans include extending network self-service, making GPU resources available as a platform service, and improving efficiency through optimized hardware selection.
The document discusses the Travel & Leisure Platform Dept and its responsibilities related to data and platform management. It provides an overview of the technical stack including private/public clouds, databases, containers, and automation/monitoring tools. It then discusses recent projects involving business continuity, containerization, alert integration, and automation. Finally, it describes open roles for a DBA and DevOps position and their responsibilities related to database provisioning, backup/recovery, infrastructure as code, and providing platforms and tools for developers.
This presentation introduces the OWASP Top 10:2021.
It explains how to look at the data related to OWASP Top 10:2021, and provides detailed explanations of items with distinctive data. It also introduces the OWASP Project related to each item.
Gora API Group technology provides a microservices architecture and APIs for Rakuten's golf course reservation system, improving the user experience and increasing customer loyalty and annual golf rounds. The architecture migrates the monolithic reservation system to microservices using Kotlin, Spring Boot, and other technologies, exposing APIs for the frontend and new products while sustaining the legacy system through services, queues, continuous delivery, and operations monitoring.