Conversational AI assistants are becoming popular and question-answering is an important part of any conversational assistant. Using relevant utterances as features in question-answering has shown to improve both the precision and recall for retrieving the right answer by a conversational assistant. Hence, utterance generation has become an important problem with the goal of generating relevant utterances (sentences or phrases) from a knowledge base article that consists of a title and a description. However, generating good utterances usually requires a lot of manual effort, creating the need for an automated utterance generation. In this paper, we propose an utterance generation system which 1) uses extractive summarization to extract important sentences from the description, 2) uses multiple paraphrasing techniques to generate a diverse set of paraphrases of the title and summary sentences, and 3) selects good candidate paraphrases with the help of a novel candidate selection algorithm.

Most social networking services support multiple types of relationships between users, such as getting connected, sending messages, and consuming feed updates. These users and relationships can be naturally represented as a dynamic multi-view network, which is a set of weighted graphs with shared common nodes but having their own respective edges. Different network views, representing structural relationship and interaction types, could have very distinctive properties individually and these properties may change due to interplay across views. Therefore, it is of interest to study how multiple views interact and affect network dynamics and, in addition, explore possible applications to social networking. In this paper, we propose approaches to capture and analyze multi-view network dynamics from various aspects. Through our proposed descriptors, we observe the synergy and cannibalization between different user groups and network views from LinkedIn dataset. We then develop models that consider the synergy and cannibalization per new relationship, and show the outperforming predictive capability of our models compared to baseline models. Finally, the proposed models allow us to understand the interplay among different views where they dynamically change over time.

Many of the world's most popular websites catalyze their growth through invitations from existing members. New members can then in turn issue invitations, and so on, creating cascades of member signups that can spread on a global scale. Although these diffusive invitation processes are critical to the popularity and growth of many websites, they have rarely been studied, and their properties remain elusive. For instance, it is not known how viral these cascades structures are, how cascades grow over time, or how diffusive growth affects the resulting distribution of member characteristics present on the site. In this paper, we study the diffusion of LinkedIn, an online professional network comprising over 332 million members, a large fraction of whom joined the site as part of a signup cascade. First we analyze the structural patterns of these signup cascades, and find them to be qualitatively different from previously studied information diffusion cascades. We also examine how signup cascades grow over time, and observe that diffusion via invitations on LinkedIn occurs over much longer timescales than are typically associated with other types of online diffusion. Finally, we connect the cascade structures with rich individual-level attribute data to investigate the interplay between the two. Using novel techniques to study the role of homophily in diffusion, we find striking differences between the local, edge-wise homophily and the global, cascade-level homophily we observe in our data, suggesting that signup cascades form surprisingly coherent groups of members.

Recommender systems have become very important for many online activities, such as watching movies, shopping for products, and connecting with friends on social networks. User behavioral analysis and user feedback (both explicit and implicit) modeling are crucial for the improvement of any online recommender system. Widely adopted recommender systems at LinkedIn such as "People You May Know" and "Endorsements" are evolving by analyzing user behaviors on impressed recommendation items.

Online social networks have become important for networking, communication, sharing, and discovery. A considerable challenge these networks face is the fact that an online social network is partially observed because two individuals might know each other, but may not have established a connection on the site. Therefore, link prediction and recommendations are important tasks for any online social network. In this paper, we address the problem of computing edge affinity between two users on a social network, based on the users belonging to organizations such as companies, schools, and online groups. We present experimental insights from social network data on organizational overlap, a novel mathematical model to compute the probability of connection between two people based on organizational overlap, and experimental validation of this model based on real social network data. We also present novel ways in which the organization overlap model can be applied to link prediction and community detection, which in itself could be useful for recommending entities to follow and generating personalized news feed.

Many applications that process social data, such as tweets, must extract entities from tweets (e.g., "Obama" and "Hawaii" in "Obama went to Hawaii"), link them to entities in a knowledge base (e.g., Wikipedia), classify tweets into a set of predefined topics, and assign descriptive tags to tweets. Few solutions exist today to solve these problems for social data, and they are limited in important ways. Further, even though several industrial systems such as OpenCalais have been deployed to solve these problems for text data, little if any has been published about them, and it is unclear if any of the systems has been tailored for social media. In this paper we describe in depth an end-to-end industrial system that solves these problems for social data. The system has been developed and used heavily in the past three years, first at Kosmix, a startup, and later at WalmartLabs. We show how our system uses a Wikipedia-based global "real-time" knowledge base that is well suited for social data, how we interleave the tasks in a synergistic fashion, how we generate and use contexts and social signals to improve task accuracy, and how we scale the system to the entire Twitter firehose. We describe experiments that show that our system outperforms current approaches. Finally we describe applications of the system at Kosmix and WalmartLabs, and lessons learned.

Search plays an important role in online social networks as it provides an essential mechanism for discovering members and content on the network. Related search recommendation is one of several mechanisms used for improving members' search experience in finding relevant results to their queries. This paper describes the design, implementation, and deployment of Metaphor, the related search recommendation system on LinkedIn, a professional social networking site with over 175~million members worldwide. Metaphor builds on a number of signals and filters that capture several dimensions of relatedness across member search activity. The system, which has been in live operation for over a year, has gone through multiple iterations and evaluation cycles. This paper makes three contributions. First, we provide a discussion of a large-scale related search recommendation system. Second, we describe a mechanism for effectively combining several signals in building a unified dataset for related search recommendations. Third, we introduce a query length model for capturing bias in recommendation click behavior. We also discuss some of the practical concerns in deploying related search recommendations.

Online social networks have enjoyed significant growth over the past several years. With improvements in mobile and Internet penetration, developing countries are participating in increasing numbers in online communities. This paper provides the first large scale and detailed analysis of social networking usage in developing country contexts. The analysis is based on data from LinkedIn, a professional social network with over 120 million members worldwide. LinkedIn has members from every country in the world, including millions in Africa, Asia, and South America. The goal of this paper is to provide researchers a detailed look at the growth, adoption, and other characteristics of social networking usage in developing countries compared to the developed world. To this end, we discuss several themes that illustrate different dimensions of social networking use, ranging from interconnectedness of members in geographic regions to the impact of local languages on social network participation.

Certain emerging network applications involve dynamically allocating shared resources to a variety of services to provide QoS guarantees for each service. Motivated by such applications, we address the following online scheduling problem belonging to the recently introduced class of reconfigurable resource scheduling problems: unit jobs of different categories arrive over time and need to be completed within category-specific delay bounds, or else they are dropped at a unit drop cost; processors can be reconfigured to process jobs of a certain category at a fixed reconfiguration cost; the goal is to minimize the total cost. We study this problem in the framework of competitive analysis. Through a novel combination of the EDF and LRU scheduling principles, we obtain an online algorithm that is constant competitive when given a constant factor resource advantage over an optimal offline algorithm.

Consider a distributed network with nodes arranged in a tree, and each node having a local value. We consider the problem of aggregating values (e.g., summing values) from all nodes to the requesting nodes in the presence of writes. The goal is to minimize the total number of messages exchanged. The key challenges are to define a notion of "acceptable" aggregate values, and to design algorithms with good performance that are guaranteed to produce such values. We formalize the acceptability of aggregate values in terms of certain consistency guarantees. We propose a lease-based aggregation mechanism, and evaluate algorithms based on this mechanism in terms of consistency and performance. With regard to consistency, we adapt the definitions of strict and causal consistency to apply to the aggregation problem. We show that any lease-based aggregation algorithm provides strict consistency in sequential executions, and causal consistency in concurrent executions. With regard to performance, we propose an online lease-based aggregation algorithm, and show that, for sequential executions, the algorithm is constant competitive against any offline algorithm that provides strict consistency. Our online lease-based aggregation algorithm is presented in the form of a fully distributed protocol, and the aforementioned consistency and performance results are formally established with respect to this protocol.

We consider a class of scheduling problems that we refer to as reconfigurable resource scheduling. This class of problems is motivated by emerging applications that involve dynamically allocating a large number of shared resources to a variety of services. We design efficient online algorithms for certain problems in this class. Our goal is to obtain constant competitive online algorithms where the online algorithm is given a constant factor advantage in terms of the number of resources. The main problem considered in this paper is as follows. The input is a sequence of requests, each of which is a set of unit jobs. Each job has a category, and needs to be processed within a fixed delay bound from its arrival, or else it is dropped and we incur a category-specific drop cost. A job of a given category can only be executed on a resource configured for that category. A resource can be reconfigured at any time at a fixed reconfiguration cost. Our main result is a constant competitive online algorithm for this problem, which is obtained by the following layered approach. First, we reduce our main problem to the special case in which all jobs arrive at integral multiples of the delay bound. Second, we reduce the latter problem to the special case of unit delay. Third, we reduce the unit-delay problem to a caching problem that we refer to as file caching with remote reads. Our solution to this caching problem generalizes certain existing work in the area of file caching.

We address a hierarchical generalization of the well-known disk paging problem. In the hierarchical cooperative caching problem, a set of n machines residing in an ultrametric space cooperate with one another to satisfy a sequence of read requests to a collection of (read-only) files. A seminal result in the area of competitive analysis states that LRU (the widely-used deterministic online paging algorithm based on the "least recently used" eviction policy) is constant-competitive if it is given a constant-factor blowup in capacity over the offline algorithm. Does such a constant-competitive deterministic algorithm (with a constant-factor blowup in the machine capacities) exist for the hierarchical cooperative caching problem? The main contribution of the present paper is to answer this question in the negative. More specifically, we establish an Ω(log log n) lower bound on the competitive ratio of any online hierarchical cooperative caching algorithm with capacity blowup O((log n)1-ε), where ε denotes an arbitrarily small positive constant.