יום רביעי, 7.6.2017, 11:30
With the rapid growth in machine-generated traffic and in storage capacities offered by Web mail services, our mailboxes get larger and larger. Search therefore becomes a critical mechanism in order to retrieve the specific messages we need. Unfortunately, during the past decade mail search has not observed the same pace of progress as Web search and is still perceived as a difficult and frustrating task. Only recently, mail search has become an emerging topic for research and has introduced new features and applications. In this talk, I will present current studies conducted over Yahoo Mail data, highlighting the characteristics of mail searchers and the types of queries they issue. I will then compare our finding to those in other domains, such as Web and Social Media, and present recent works in search results ranking as well as in query suggestion, published in top-tier data-science conferences.
Ariel Raviv is a Senior Research Engineer at Yahoo Research, where he engages in mail search activities such as relevance ranking, top results selection, and query suggestion. Before joining Yahoo, Ariel was a Research Engineer at IBM Research in Israel, where he worked on recommendation systems, large-scale crawling, machine learning, search and classification tasks, as a member of the Information Retrieval and Social Technologies group. He received his B.Sc and M.Sc from the Dept. of Computer Science, Technion - Israel Institute of Technology, Haifa, where he conducted research under the supervision of Prof. Shaul Markovitch in the field of Artificial Intelligence and Natural Language Processing. Ariel is passionate about data mining and information retrieval, and has several related patents as well as several publications in leading conferences including AAAI, WWW, SIGIR, CIKM and RecSys.