Richard Berendsen

On the assessment of expertise profiles

Expertise retrieval has attracted significant interest in the field of information retrieval. Expert finding has been studied extensively, with less attention going to the complementary task of expert profiling, that is, automatically identifying topics about which a person is knowledgeable. We describe a test collection for expert profiling in which expert users have self-selected their knowledge areas. Motivated by the sparseness of this set of knowledge areas, we report on an assessment experiment in which academic experts judge a profile that has been automatically generated by state-of-the-art expert-profiling algorithms; optionally, experts can indicate a level of expertise for relevant areas. Experts may also give feedback on the quality of the systemgenerated knowledge areas. We report on a content analysis of these comments and gain insights into what aspects of profiles matter to experts. We provide an error analysis of the system-generated profiles, identifying factors that help explain why certain experts may be harder to profile than others. We also analyze the impact on evaluating expert-profiling systems of using selfselected versus judged system-generated knowledge areas as ground truth; they rank systems somewhat differently but detect about the same amount of pairwise significant differences despite the fact that the judged system-generated assessments are more sparse.

Pseudo test collections for training and tuning microblog rankers

Recent years have witnessed a persistent interest in generating pseudo test collections, both for training and evaluation purposes. We describe a method for generating queries and relevance judgments for microblog search in an unsupervised way. Our starting point is this intuition: tweets with a hashtag are relevant to the topic covered by the hashtag and hence to a suitable query derived from the hashtag. Our baseline method selects all commonly used hashtags, and all associated tweets as relevance judgments; we then generate a query from these tweets. Next, we generate a timestamp for each query, allowing us to use temporal information in the training process. We then enrich the generation process with knowledge derived from an editorial test collection for microblog search. We use our pseudo test collections in two ways. First, we tune parameters of a variety of well known retrieval methods on them. Correlations with parameter sweeps on an editorial test collection are high on average, with a large variance over retrieval algorithms. Second, we use the pseudo test collections as training sets in a learning to rank scenario. Performance close to training on an editorial test collection is achieved in many cases. Our results demonstrate the utility of tuning and training microblog search algorithms on automatically generated training material.

A syntax-aware re-ranker for microblog retrieval

We tackle the problem of improving microblog retrieval algorithms by proposing a robust structural representation of (query, tweet) pairs. We employ these structures in a principled kernel learning framework that automatically extracts and learns highly discriminative features. We test the generalization power of our approach on the TREC Microblog 2011 and 2012 tasks. We find that relational syntactic features generated by structural kernels are effective for learning to rank (L2R) and can easily be combined with those of other existing systems to boost their accuracy. In particular, the results show that our L2R approach improves on almost all the participating systems at TREC, only using their raw scores as a single feature. Our method yields an average increase of 5% in retrieval effectiveness and 7 positions in system ranks.

Result disambiguation in web people search

We study the problem of disambiguating the results of a web people search engine: given a query consisting of a person name plus the result pages for this query, find correct referents for all mentions by clustering the pages according to the different people sharing the name. While the problem has been studied extensively, we discover that the increasing availability of results retrieved from social media platforms causes state-of-the-art methods to break down. We analyze the problem and propose a dual strategy where we distinguish between results obtained from social media platforms and those obtained from other sources. In our dual strategy, the two types of documents are disambiguated separately, using different strategies, and their results are then merged. We study several instantiations for the different stages in our proposed strategy and manage to achieve state-of-the-art performance.

PROMISE retreat report prospects and opportunities for information access evaluation

The PROMISE network of excellence organized a two-days brainstorming workshop on 30th and 31st May 2012 in Padua, Italy, to discuss and envisage future directions and perspectives for the evaluation of information access and retrieval systems in multiple languages and multiple media. This document reports on the outcomes of this event and provides details about the six envisaged research lines: search applications; contextual evaluation; challenges in test collection design and exploitation; component-based evaluation; ongoing evaluation; and signal-aware evaluation. The ultimate goal of the PROMISE retreat is to stimulate and involve the research community along these research lines and to provide funding agencies with effective and scientifically sound ideas for coordinating and supporting information access research.

Generating pseudo test collections for learning to rank scientific articles

Pseudo test collections are automatically generated to provide training material for learning to rank methods. We propose a method for generating pseudo test collections in the domain of digital libraries, where data is relatively sparse, but comes with rich annotations. Our intuition is that documents are annotated to make them better findable for certain information needs. We use these annotations and the associated documents as a source for pairs of queries and relevant documents. We investigate how learning to rank performance varies when we use different methods for sampling annotations, and show how our pseudo test collection ranks systems compared to editorial topics with editorial judgements. Our results demonstrate that it is possible to train a learning to rank algorithm on generated pseudo judgments. In some cases, performance is on par with learning on manually obtained ground truth.

Classifying queries submitted to a vertical search engine

We propose and motivate a scheme for classifying queries submitted to a people search engine. We specify a number of features for automatically classifying people queries into the proposed classes and examine the effectiveness of these features. Our main finding is that classification is feasible and that using information from past searches, clickouts and news sources is important.