Pinwheel graphic representing the Microsoft Research Summit

Return to Event: Microsoft Research Summit 2021

Microsoft Research Summit 2021 • Videos

Research talk: System frontiers for dense retrieval

The Microsoft Bing search engine combines classic information retrieval and dense retrieval in multiple stages of the search funnel. Handling hundreds of billions of documents with constant updates creates massive system challenges to inference, search, and ranking. In this talk, we’ll present current and ongoing approaches and suggest research challenges to effectively combine dense and sparse retrieval at large scale.

Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit (opens in new tab)

Event:: Microsoft Research Summit 2021
Track:: The Future of Search & Recommendation
Date:: October 19, 2021
Speakers:: Jason Li, Knut Risvik
Affiliation:: Microsoft

- Jason Li
  
  Software Engineer
- Knut Magne Risvik
  
  Distinguished Engineer
Research Area
Event
- Microsoft Research Summit 2021

The Future of Search & Recommendation

Opening remarks: The Future of Search and Recommendation
October 19, 2021
Speakers:

Susan Dumais
Keynote: Universal search and recommendation
October 19, 2021
Speakers:

Paul Bennett
Keynote: Extreme classification for dense retrieval and personalized recommendation
October 19, 2021
Speakers:

Manik Varma
Research talk: Capturing the visual evolution of fashion in space and time
October 19, 2021
Speakers:

Kristen Grauman
Research talk: Local factor models for large-scale inductive recommendation
October 19, 2021
Speakers:

Tobias Schnabel
Research talk: Learning and pretraining strategies for dense retrieval in search and beyond
October 19, 2021
Speakers:

Chenyan Xiong
Research talk: DeepXML: A deep extreme classification framework for recommending hundreds of millions of items
October 19, 2021
Speakers:

Deepak Saini
Research talk: Is phrase retrieval all we need?
October 19, 2021
Speakers:

Danqi Chen
Research talk: Approximate nearest neighbor search systems at scale
October 19, 2021
Speakers:

Harsha Simhadri
Research talk: SPTAG++: Fast hundreds of billions-scale vector search with millisecond response time
October 19, 2021
Speakers:

Qi Chen
Research talk: System frontiers for dense retrieval
October 19, 2021
Speakers:

Jason Li,

Knut Magne Risvik
Research talk: Search, summarization, and sensemaking
October 19, 2021
Speakers:

Marti Hearst
Research talk: IGLU: Interactive grounded language understanding in a collaborative environment
October 19, 2021
Speakers:

Julia Kiseleva
Research talk: Summarizing information across multiple documents and modalities
October 19, 2021
Speakers:

Subhojit Som
Research talk: The science behind semantic search: How AI from Microsoft Bing is powering Azure Cognitive Search
October 19, 2021
Speakers:

Alec Berntson
Research talk: Domain-specific pretraining for vertical search
October 19, 2021
Speakers:

Tristan Naumann
Panel: The future of search and recommendation: Beyond web search
October 19, 2021
Speakers:

Eric Horvitz,

Nitin Agrawal,

Soumen Chakrabati

, et. al.
Research talk: Extracting pragmatics from content interactions to improve enterprise recommendations
October 19, 2021
Speakers:

Jennifer Neville
Research talk: Challenges in multi-tenant graph representation learning for recommendation problems
October 19, 2021
Speakers:

Arun Iyer
Research talk: Attentive knowledge-aware graph neural networks for recommendation
October 19, 2021
Speakers:

Yaming Yang
Panel: Causality in search and recommendation systems
October 19, 2021
Speakers:

Emre Kiciman,

Amit Sharma,

Dean Eckles

, et. al.
Closing remarks: The Future of Search and Recommendation
October 19, 2021
Speakers:

Susan Dumais