Research talk: Extracting pragmatics from content interactions to improve enterprise recommendations
Data trails, recording the way that people interact with content and with each other in an enterprise, are a source of linguistic pragmatics (cues to language meaning implied by social interactions) that can be used to improve search and recommendation, particularly in tail scenarios. Graph ML methods are uniquely positioned to be able to learn from these data trails by jointly considering multiple modalities of interaction data, and collectively propagating pragmatics across teams/organizations. In this talk, we will present our recent research incorporating these signals into GNN methods—to learn jointly from content and relational interactions.
Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit (opens in new tab)
- 轨迹:
- The Future of Search & Recommendation
- 日期：
- 演讲者：
- Jennifer Neville
- 所属机构：
- Microsoft Research Redmond
-
-
Jennifer Neville
Partner Research Manager
-
-
The Future of Search & Recommendation
-
-
Keynote: Universal search and recommendation
Speakers:- Paul Bennett
-
-
-
-
Research talk: Learning and pretraining strategies for dense retrieval in search and beyond
Speakers:- Chenyan Xiong
-
-
Research talk: Is phrase retrieval all we need?
Speakers:- Danqi Chen
-
-
-
-
-
Research talk: IGLU: Interactive grounded language understanding in a collaborative environment
Speakers:- Julia Kiseleva
-
Research talk: Summarizing information across multiple documents and modalities
Speakers:- Subhojit Som
-
-
-
Panel: The future of search and recommendation: Beyond web search
Speakers:- Eric Horvitz,
- Nitin Agrawal,
- Soumen Chakrabati
-
-
-
Research talk: Attentive knowledge-aware graph neural networks for recommendation
Speakers:- Yaming Yang
-
Panel: Causality in search and recommendation systems
Speakers:- Emre Kiciman,
- Amit Sharma,
- Dean Eckles
-
