Abstract: Expert search is a task of growing importance in Enterprise settings. In a classical search setting, users normally require relevant documents to fulfil an information need. However, in Enterprise settings, users also have a need to identify the co-workers with relevant expertise to a topic area. An expert search engine assists users with their expertise need, by ranking candidate experts with respect to their predicted expertise about a topic of interest. This work presents a novel model for the expert search, based on a Bayesian belief network. We show how the proposed model can generate several different strategies for ranking candidates by their predicted expertise with respect to a query. The Bayesian belief network model for expert search proposed here is general, as it can be extended in the future to take into account various other types of evidence in the expert search task, such as the social aspect of expert search, where people work within groups and co-author publications. 1

In TREC 2007, we participate in four tasks of the Blog and Enterprise tracks. We continue experiments using Terrier 1 [14], our modular and scalable Information Retrieval (IR) platform, and the Divergence From Randomness (DFR) framework. In particular, for the Blog track opinion finding task, we propose a statistical term weighting approach to identify opinionated documents. An alternative approach based on an opinion identification tool is also utilised. Overall, a 15 % improvement over a non-opinionated baseline is observed in applying the statistical term weighting approach. In the Expert Search task of the Enterprise track, we investigate the use of proximity between query terms and candidate name occurrences in documents. 1.

Information retrieval systems often use proximity or term dependence models to increase the effectiveness of document retrieval. Many of the existing proximity models examine document-level local statistics, such as the frequencies that pairs of query terms occur within fixed-size windows of each document, before applying standard or adapted weighting functions – for instance Markov Random Fields. Term weighting models use Inverse Document Frequency (IDF) to control the influence of occurrences of different query terms in documents. Similarly, some proximity models also take into account the frequency of pairs of query terms in the entire corpus of documents. However, pair frequency is an expensive statistic to pre-compute at indexing time, or to compute at retrieval time before scoring documents. In this work, we examine in a uniform setting, the importance of such global statistics for proximity weighting. We investigate two sources of global statistics, namely the target corpus, and the entire Web. Experiments are conducted using the TREC GOV2 and ClueWeb09 test collections. Our results show that local statistics alone are sufficient for effective retrieval, and global statistics usually do not bring any significant improvement in effectiveness, compared to the same proximity approaches that do not use these global statistics.

In TREC 2009, we extend our Voting Model for the faceted blog distillation, top stories identification, and related entity finding tasks. Moreover, we experiment with our novel xQuAD framework for search result diversification. Besides fostering our research in multiple directions, by participating in such a wide portfolio of tracks, we further develop the indexing and retrieval capabilities of our Terrier Information Retrieval platform, to effectively and efficiently cope with a new generation of large-scale test collections. 1.

Feedback tracks. In all tracks, we continue the research and development of the Terrier platform 1 centred around extending state-of-the-art weighting models based on the Divergence From