Showing papers by "Andrei Z. Broder published in 2018"

Learning Effective Embeddings for Machine Generated Emails with Applications to Email Category Prediction

Abstract: Machine generated business-to-consumer (B2C) emails such as receipts, newsletters, and promotions constitute a large portion of users’ inboxes today. These emails reflect the users’ interests and often are sequentially correlated, e.g., users interested in relocating may receive a sequence of messages on housing, moving, job availability, etc. We aim to infer (and eventually serve) the users’ future interests by predicting the categories of their future emails. There are many useful methods, such as recurrent neural networks, that can be applied for such predictions, but in all cases the key to better performance is an effective representation of emails and users. To this end, we propose a general framework for learning embeddings for emails and users, using as input only the sequence of B2C templates users receive and open. (A template is a B2C email stripped of all transient information related to specific users.) These learned embeddings allow us to identify both sequentially correlated emails and users with similar sequential interests. We can also use the learned embeddings either as input features or embedding initializers for email category prediction tasks. Extensive experiments with millions of fully anonymized B2C emails demonstrate that the learned embeddings can significantly improve the prediction accuracy for future email categories. We hope that this effective yet simple embedding learning framework will inspire new machine intelligence applications that will improve the users’ email experience.

A Call to Arms: Embrace Assistive AI Systems!

Abstract: A quarter-century ago Web search stormed the world: within a few years the Web search box became a standard tool of daily life ready to satisfy informational, transactional, and navigational queries needed for some task completion. However, two recent trends are dramatically changing the box»s role: first, the explosive spread of smartphones brings significant computational resources literally into the pockets of billions of users; second, recent technological advances in machine learning and artificial intelligence, and in particular in speech processing led to the wide deployment of assistive AI systems, culminating in personal digital assistants. Along the way, the "Web search box" has become an "assistance request box" (implicit, in the case of voice-activated assistants) and likewise, many other information processing systems (e.g. e-mail, navigation, personal search, etc) have adopted assistive aspects. Formally, the assistive systems can be viewed as a selection process within a base set of alternatives driven by some user input. The output is either one alternative or a smaller set of alternatives, maybe subject to future selection. Hence, classic IR is a particular instance of this formulation, where the input is a textual query and the selection process is relevance ranking over the corpus. In increasing order of selection capabilities, assistive systems can be classified into three categories: Subordinate : systems where the selection is fully specified by the request; if this results in a singleton the system provides it, otherwise the system provides a random alternative from the result set. Therefore, the challenge for subordinate systems consists only in the correct interpretation of the user request (e.g., weather information, simple personal schedule management, a "play jazz" request). Conducive : systems that reduce the set of alternatives to a smaller set, possibly via an interactive process (e.g. the classic ten blue links, the three "smart replies" in Gmail, interactive recommendations, etc). Decisive : systems that make all necessary decisions to reach the desired goal (in other words, select a single alternative from the set of possibilities) including resolving ambiguities and other substantive decisions without further input from the user (e.g., typical translation systems, self-driving cars). The main goal of this talk is to examine these developments and to urge the WSDM community to increase its focus on assistive AI solutions that are becoming pertinent to a wide variety of information processing problems. I will mostly present ideas and work in progress, and there will be many more open questions than definitive answers.