GSB'15: First International Workshop on Graph Search and Beyond

Proceedings

Published as CEUR WS: http://ceur-ws.org/Vol-1393/.

Program

The program consisted of invited keynotes, short paper presentations, breakout groups, and a report out and final discussion.

Invited Speakers

• Rose Marie Philip (Facebook), Personalized Post Search at Facebook [Slides].

  There are over a billion people and over a trillion posts on Facebook. Among these posts, there are uniquely personalized answers to many search queries. The goal of Facebook post search is to help people find the most personally relevant posts for each individual query, tailored to the content of people's networks. In this talk, I will present some of our work to build a search product that uses personalized graph signals in ranking. I will also give an overview of query modification, posts retrieval and ranking of results.

• Swee Lim (Linkedin), Graph Search at Linkedin [Slides].

  Linkedin is the largest professional social network. Linkedin's graph and search systems help our users discover other users, jobs, companies, schools, and relevant professional information. I will present the evolution of these systems, how they support current use cases, their strengths and weaknesses, our next generation systems, and how we intend to leverage these systems to perform graph searches.

• Doug Oard (University of Maryland), Good Uses for Crummy Knowledge Graphs [Slides].

  In 1993, Ken Church and Ed Hovy suggested that before we ask how well some new technology meets the need we envision for it, we should pause and first reflect on the question of whether---now that we know something about what can be built---we are envisioning the right uses for what we have. They titled their paper Good Applications for Crummy Machine Translation. At about that same time, information retrieval researchers obliged them by (generally without having read their paper) starting to work on cross-language information retrieval; arguably the best application for crummy machine translation ever invented. Now we have some crummy knowledge graphs---and this time we have read the Church and Hovy paper---so perhaps the time is right for us to ask whether we have yet envisioned good uses for crummy knowledge graphs. In this talk, I will seek to seed that discussion.

• Alex Wade (Microsoft), Overview of Microsoft Academic Graph [Slides].

  The Microsoft Academic Graph is a heterogeneous graph containing scientific publication records, citation relationships between those publications, as well as authors, institutions, journals and conference "venues" and fields of study.