The task addressed in this paper, finding experts in an enterprise setting, has gained in importance and interest over the past few years. Commonly, this task is approached as an association finding exercise between people and topics. Existing techniques use either documents (as a whole) or proximity-based techniques to represent candidate experts. Proximity-based techniques have shown clear precision-enhancing benefits. We complement both document and proximity-based approaches to expert finding by importing global evidence of expertise, i.e., evidence obtained using information that is not available in the immediate proximity of a candidate expert’s name occurrence or even on the same page on which the name occurs. Examples include candidate priors, query models, as well as other documents a candidate expert is associated with. Using the CERC data set created for the TREC 2007 Enterprise track we identify examples of non-local evidence of expertise. We then propose modified expert retrieval models that are capable of incorporating both local (either document or snippet-based) evidence and non-local evidence of expertise. Results show that our refined models significantly outperform existing state-of-the-art approaches.

Match-making systems refer to systems where users want to meet other individuals to satisfy some underlying need. Examples of match-making systems include dating services, resume/job bulletin boards, community based question answering, and consumer-to-consumer marketplaces. One fundamental component of a match-making system is the retrieval and ranking of candidate matches for a given user. We present the first in-depth study of information retrieval approaches applied to match-making systems. Specifically, we focus on retrieval for a dating service. This domain offers several unique problems not found in traditional information retrieval tasks. These include two-sided relevance, very subjective relevance, extremely few relevant matches, and structured queries. We propose a machine learned ranking function that makes use of features extracted from the uniquely rich user profiles that consist of both structured and unstructured attributes. An extensive evaluation carried out using data gathered from a real online dating service shows the benefits of our proposed methodology with respect to traditional match-making baseline systems. Our analysis also provides deep insights into the aspects of match-making that are particularly important for producing highly relevant matches.

The retrieval effectiveness of the underlying document search component of an expert search engine can have an important impact on the effectiveness of the generated expert search results. In this large-scale study, we perform novel experiments in the context of the document search and expert search tasks of the TREC Enterprise track, to measure the influence that the performance of the document ranking has on the ranking of candidate experts. In particular, we show, using real and simulated document rankings, that while the expert search system performance is related to the relevance of the retrieved documents, surprisingly, it is not always the case that increasing document search effectiveness causes an increase in expert search performance.

Abstract not found

Abstract. Users often search for entities instead of documents and in this setting are willing to provide extra input, in addition to a query, such as category information and example entities. We propose a general probabilistic framework for entity search to evaluate and provide insight in the many ways of using these types of input for query modeling. We focus on the use of category information and show the advantage of a category-based representation over a term-based representation, and also demonstrate the effectiveness of category-based expansion using example entities. Our best performing model shows very competitive performance on the INEX-XER entity ranking and list completion tasks. 1

Abstract: We describe our participation in the TREC 2008 Enterprise track and detail our language modeling-based approaches. For document search, our focus was on query expansion using profiles of top ranked experts and on document priors. We found that these techniques result in small, but noticeable improvements over our baseline method. For expert search, we combine candidate- and document-based models, and also bring in web evidence. We found that the combined models significantly and consistently outperformed our very competitive baseline models. 1

Abstract not found

Meeting notes are documents which contain lots of structure. This structure is often implicit in layout and reserved words. On the other hand, since meetings tend to occur regularly and are repeated for long periods of time, this structure is often (semi-)formalized. This makes these documents suitable for automatic semantic annotation efforts. We describe the annotation we performed on the notes of more than 20 years of Dutch parliamentary debates. We annotated every word spoken in parliament with 1) the speaker, 2) her party at the time of speaking, 3) her role/function in parliament and 4) the iso-date. These annotations yield numerous new ways of searching, browsing, mining and summarizing these documents. Meetings are always too long, whence so are their verbatim notes. But of course they contain valuable information and notes have to be consulted from time to time. In this paper we show that semantic annotation can make finding things easier, and more fun. 1.

In this paper we investigate the task of Entity Ranking on the Web. Searchers looking for entities are arguably better served by presenting a ranked list of entities directly, rather than a list of web pages with relevant but also potentially redundant information about these entities. Since entities are represented by their web homepages, a naive approach to entity ranking is to use standard text retrieval. Our experimental results clearly demonstrate that text retrieval is effective at finding relevant pages, but performs poorly at finding entities. Our proposal is to use Wikipedia as a pivot for finding entities on the Web, allowing us to reduce the hard web entity ranking problem to easier problem of Wikipedia entity ranking. Wikipedia allows us to properly identify entities and some of their characteristics, and Wikipedia’s elaborate category structure allows us to get a handle on the entity’s type. Our main

Abstract: We describe the participation of the University of Amsterdam’s ILPS group in the blog, enterprise and relevance feedback track at TREC 2008. Our main preliminary conclusions are that estimating mixture weights for external expansion in blog post retrieval is non-trivial and we need more analysis to find out why it works better for blog distillation than for blog post retrieval. For the relevance feedback track we observe two things: (i) in terms of statMAP, a larger number of judged non-relevant documents improves retrieval effectiveness and (ii) on the TREC Terabyte topics, we can effectively replace the estimates on the judged non-relevant documents with estimations on the document collection. Finally, since the enterprise track did not have any results yet, we only described our participation and do not draw any conclusions. 1