Evaluation measures act as objective functions to be optimized by information retrieval systems. Such objective functions must accurately reflect user requirements, particularly when tuning IR systems and learning ranking functions. Ambiguity in queries and redundancy in retrieved documents are poorly reflected by current evaluation measures. In this paper, we present a framework for evaluation that systematically rewards novelty and diversity. We develop this framework into a specific evaluation measure, based on cumulative gain. We demonstrate the feasibility of our approach using a test collection based on the TREC question answering track.

We present a static index pruning method, to be used in ad-hoc document retrieval tasks, that follows a documentcentric approach to decide whether a posting for a given term should remain in the index or not. The decision is made based on the term's contribution to the document's Kullback-Leibler divergence from the text collection's global language model. Our technique can be used to decrease the size of the index by over 90%, at only a minor decrease in retrieval effectiveness. It thus allows us to make the index small enough to fit entirely into the main memory of a single PC, even for large text collections containing millions of documents. This results in great efficiency gains, superior to those of earlier pruning methods, and an average response time around 20 ms on the GOV2 document collection.

No abstract

Information retrieval evaluation based on the pooling method is inherently biased against systems that did not contribute to the pool of judged documents. This may distort the results obtained about the relative quality of the systems evaluated and thus lead to incorrect conclusions about the performance of a particular ranking technique.We examine the magnitude of this effect and explore how it can be countered by automatically building an unbiased set of judgements from the original, biased judgements obtained through pooling. We compare the performance of this method with other approaches to the problem of incomplete judgements, such as bpref, and show that the proposed method leads to higher evaluation accuracy, especially if the set of manual judgements is rich in documents, but highly biased against some systems.

We present a new family of hybrid index maintenance strategies to be used in on-line index construction for monotonically growing text collections. These new strategies improve upon recent results for hybrid index maintenance in dynamic text retrieval systems. Like previous techniques, our new method distinguishes between short and long posting lists: While short lists are maintained using a merge strategy, long lists are kept separate and are updated in-place. This way, costly relocations of long posting lists are avoided.We discuss the shortcomings of previous hybrid methods and give an experimental evaluation of the new technique, showing that its index maintenance performance is superior to that of the earlier methods, especially when the amount of main memory available to the indexing system is small. We also present a complexity analysis which proves that, under a Zipfian term distribution, the asymptotical number of disk accesses performed by the best hybrid maintenance strategy is linear in the size of the text collection, implying the asymptotical optimality of the proposed strategy.