Hugo Zaragoza

The Probabilistic Relevance Framework: BM25 and Beyond

The Probabilistic Relevance Framework (PRF) is a formal framework for document retrieval, grounded in work done in the 1970—1980s, which led to the development of one of the most successful text-retrieval algorithms, BM25. In recent years, research in the PRF has yielded new retrieval models capable of taking into account document meta-data (especially structure and link-graph information). Again, this has led to one of the most successful Web-search and corporate-search algorithms, BM25F. This work presents the PRF from a conceptual point of view, describing the probabilistic modelling assumptions behind the framework and the different ranking algorithms that result from its application: the binary independence model, relevance feedback models, BM25 and BM25F. It also discusses the relation between the PRF and other statistical models for IR, and covers some related topics, such as the use of non-textual features, and parameter optimisation for models with free parameters.

Simple BM25 extension to multiple weighted fields

This paper describes a simple way of adapting the BM25 ranking formula to deal with structured documents. In the past it has been common to compute scores for the individual fields (e.g. title and body) independently and then combine these scores (typically linearly) to arrive at a final score for the document. We highlight how this approach can lead to poor performance by breaking the carefully constructed non-linear saturation of term frequency in the BM25 function. We propose a much more intuitive alternative which weights term frequencies <i>before</i> the non-linear term frequency saturation function is applied. In this scheme, a structured document with a title weight of two is mapped to an unstructured document with the title content repeated twice. This more verbose unstructured document is then ranked in the usual way. We demonstrate the advantages of this method with experiments on Reuters Vol1 and the TREC dotGov collection.

Relevance weighting for query independent evidence

A query independent feature, relating perhaps to document content, linkage or usage, can be transformed into a static, per-document relevance weight for use in ranking. The challenge is to find a good function to transform feature values into relevance scores. This paper presents FLOE, a simple density analysis method for modelling the shape of the transformation required, based on training data and without assuming independence between feature and baseline. For a new query independent feature, it addresses the questions: is it required for ranking, what sort of transformation is appropriate and, after adding it, how successful was the chosen transformation? Based on this we apply sigmoid transformations to PageRank, indegree, URL Length and ClickDistance, tested in combination with a BM25 baseline.

Ad-hoc object retrieval in the web of data

Semantic Search refers to a loose set of concepts, challenges and techniques having to do with harnessing the information of the growing Web of Data (WoD) for Web search. Here we propose a formal model of one specific semantic search task: ad-hoc object retrieval. We show that this task provides a solid framework to study some of the semantic search problems currently tackled by commercial Web search engines. We connect this task to the traditional ad-hoc document retrieval and discuss appropriate evaluation metrics. Finally, we carry out a realistic evaluation of this task in the context of a Web search application.

Parsimonious language models for information retrieval

We systematically investigate a new approach to estimating the parameters of language models for information retrieval, called parsimonious language models. Parsimonious language models explicitly address the relation between levels of language models that are typically used for smoothing. As such, they need fewer (non-zero) parameters to describe the data. We apply parsimonious models at three stages of the retrieval process: 1) at indexing time; 2) at search time; 3) at feedback time. Experimental results show that we are able to build models that are significantly smaller than standard models, but that still perform at least as well as the standard approaches.

Learning to rank answers to non-factoid questions from web collections

This work investigates the use of linguistically motivated features to improve search, in particular for ranking answers to non-factoid questions. We show that it is possible to exploit existing large collections of question–answer pairs (from online social Question Answering sites) to extract such features and train ranking models which combine them effectively. We investigate a wide range of feature types, some exploiting natural language processing such as coarse word sense disambiguation, named-entity identification, syntactic parsing, and semantic role labeling. Our experiments demonstrate that linguistic features, in combination, yield considerable improvements in accuracy. Depending on the system settings we measure relative improvements of 14% to 21% in Mean Reciprocal Rank and Precision@1, providing one of the most compelling evidence to date that complex linguistic features such as word senses and semantic roles can have a significant impact on large-scale information retrieval tasks.

Ranking very many typed entities on wikipedia

We discuss the problem of ranking very many entities of different types. In particular we deal with a heterogeneous set of types, some being very generic and some very specific. We discuss two approaches for this problem: i) exploiting the entity containment graph and ii) using a Web search engine to compute entity relevance. We evaluate these approaches on the real task of ranking Wikipedia entities typed with a state-of-the-art named-entity tagger. Results show that both approaches can greatly increase the performance of methods based only on passage retrieval.

Optimisation methods for ranking functions with multiple parameters

Optimising the parameters of ranking functions with respect to standard IR rank-dependent cost functions has eluded satisfactory analytical treatment. We build on recent advances in alternative differentiable pairwise cost functions, and show that these techniques can be successfully applied to tuning the parameters of an existing family of IR scoring functions (BM25), in the sense that we cannot do better using sensible search heuristics that directly optimize the rank-based cost function NDCG. We also demonstrate how the size of training set affects the number of parameters we can hope to tune this way.

Early exit optimizations for additive machine learned ranking systems

Some commercial web search engines rely on sophisticated machine learning systems for ranking web documents. Due to very large collection sizes and tight constraints on query response times, online efficiency of these learning systems forms a bottleneck. An important problem in such systems is to speedup the ranking process without sacrificing much from the quality of results. In this paper, we propose optimization strategies that allow short-circuiting score computations in additive learning systems. The strategies are evaluated over a state-of-the-art machine learning system and a large, real-life query log, obtained from Yahoo!. By the proposed strategies, we are able to speedup the score computations by more than four times with almost no loss in result quality.

Bayesian extension to the language model for ad hoc information retrieval

We propose a Bayesian extension to the ad-hoc Language Model. Many smoothed estimators used for the multinomial query model in ad-hoc Language Models (including Laplace and Bayes-smoothing) are approximations to the Bayesian predictive distribution. In this paper we derive the full predictive distribution in a form amenable to implementation by classical IR models, and then compare it to other currently used estimators. In our experiments the proposed model outperforms Bayes-smoothing, and its combination with linear interpolation smoothing outperforms all other estimators.