Reciprocal Rank Fusion (RRF), a simple method for combining the document rankings from multiple IR systems, consistently yields better results than any individual system, and better results than the standard method Condorcet Fuse. This result is demonstrated by using RRF to combine the results of several TREC experiments, and to build a meta-learner that ranks the LETOR 3 dataset better than any previously reported method

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.

Index compression techniques are known to substantially decrease the storage requirements of a text retrieval system. As a side-effect, they may increase its retrieval performance by reducing disk I/O overhead. Despite this advantage, developers sometimes choose to store index data in uncompressed form, in order to not obstruct random access into each index term's postings list.

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.

For enterprise search, there exists a relationship between work task and document type that can be used to refine search results. In this poster, we adapt the popular Okapi BM25 scoring function to weight term frequency based on the relevance of a document type to a work task. Also, we use click frequency for each task-type pair to estimate a realistic weight. Using the W3C collection from the TREC Enterprise track for evaluations, our approach leads to significant improvements on search precision.

We present a static index pruning method, to be used in ad-hoc document retrieval tasks, that follows a document-centric 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.

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.

We propose an integration of term proximity scoring into Okapi BM25. The relative retrieval effectiveness of our retrieval method, compared to pure BM25, varies from collection to collection.We present an experimental evaluation of our method and show that the gains achieved over BM25 as the size of the underlying text collection increases. We also show that for stemmed queries the impact of term proximity scoring is larger than for unstemmed queries.

We examine issues in the design of fully dynamic information retrieval systems supporting both document insertions and deletions. The two main components of such a system, index maintenance and query processing, affect each other, as high query performance is usually paid for by additional work during update operations. Two aspects of the system -- incremental updates and garbage collection for delayed document deletions -- are discussed, with a focus on the respective indexing vs. query performance trade-offs. Depending on the relative number of queries and update operations, different strategies lead to optimal overall performance.