Naama Kraus

Context-sensitive query auto-completion

Query auto completion is known to provide poor predictions of the users query when her input prefix is very short (e.g., one or two characters). In this paper we show that context, such as the users recent queries, can be used to improve the prediction quality considerably even for such short prefixes. We propose a context-sensitive query auto completion algorithm, NearestCompletion, which outputs the completions of the users input that are most similar to the context queries. To measure similarity, we represent queries and contexts as high-dimensional term-weighted vectors and resort to cosine similarity. The mapping from queries to vectors is done through a new query expansion technique that we introduce, which expands a query by traversing the query recommendation tree rooted at the query. In order to evaluate our approach, we performed extensive experimentation over the public AOL query log. We demonstrate that when the recent users queries are relevant to the current query she is typing, then after typing a single character, NearestCompletions MRR is 48% higher relative to the MRR of the standard MostPopularCompletion algorithm on average. When the context is irrelevant, however, NearestCompletions MRR is essentially zero. To mitigate this problem, we propose HybridCompletion, which is a hybrid of NearestCompletion with MostPopularCompletion. HybridCompletion is shown to dominate both NearestCompletion and MostPopularCompletion, achieving a total improvement of 31.5% in MRR relative to MostPopularCompletion on average.

A service delivery platform for server management services

Computer server management is an important component of the global IT (information technology) services business. The providers of server management services face unrelenting efficiency challenges in order to remain competitive with other providers. Server system administrators (SAs) represent the majority of the workers in this industry, and their primary task is server management. Since system administration is a highly skilled position, the costs of employing such individuals are high, and thus, the challenge is to increase their efficiency so that a given SA can manage larger numbers of servers. In this paper, we describe a widely deployed Service Delivery Portal (SDP) in use throughout the Server Systems Operations business of IBM that provides a set of well-integrated technologies to help SAs perform their tasks more efficiently. The SDP is based on three simple design principles: 1) user interface aggregation, 2) data aggregation, and 3) knowledge centralization. This paper describes the development of the SDP from the vantage point of these three basic design principles along with lessons learned and the impact assessed from studying the behavior of SAs with and without the tool.

NearBucket-LSH: Efficient Similarity Search in P2P Networks

We present NearBucket-LSH, an effective algorithm for similarity search in large-scale distributed online social networks organized as peer-to-peer overlays. As communication is a dominant consideration in distributed systems, we focus on minimizing the network cost while guaranteeing good search quality. Our algorithm is based on Locality Sensitive Hashing (LSH), which limits the search to collections of objects, called buckets, that have a high probability to be similar to the query. More specifically, NearBucket-LSH employs an LSH extension that searches in near buckets, and improves search quality but also significantly increases the network cost. We decrease the network cost by considering the internals of both LSH and the P2P overlay, and harnessing their properties to our needs. We show that our NearBucket-LSH increases search quality for a given network cost compared to previous art. In many cases, the search quality increases by more than 50%.