It is well known in statistics and machine learning that the combination of latent (or hidden) variables and observed variables offer more expressive power than models with observed variables alone. Latent variables

This paper aims to conduct a study on the listwise approach to learning to rank. The listwise approach learns a ranking function by taking individual lists as instances and minimizing a loss function defined on the predicted list and the ground-truth list. Existing work on the approach mainly focused on the development of new algorithms; methods such as RankCosine and ListNet have been proposed and good performances by them have been observed. Unfortunately, the underlying theory was not sufficiently studied so far. To amend the problem, this paper proposes conducting theoretical analysis of learning to rank algorithms through investigations on the properties of the loss functions, including consistency, soundness, continuity, differentiability, convexity, and efficiency. A sufficient condition on consistency for ranking is given, which seems to be the first such result obtained in related research. The paper then conducts analysis on three loss functions: likelihood loss, cosine loss, and cross entropy loss. The latter two were used in RankCosine and ListNet. The use of the likelihood loss leads to the development of

Many machine learning technologies such as support vector machines, boosting, and neural networks have been applied to the ranking problem in information retrieval. However, since originally the methods were not developed for this task, their loss functions do not directly link to the criteria used in the evaluation of ranking. Specifically, the loss functions are defined on the level of documents or document pairs, in contrast to the fact that the evaluation criteria are defined on the level of queries. Therefore, minimizing the loss functions does not necessarily imply enhancing ranking performances. To solve this problem, we propose using query-level loss functions in learning of ranking functions. We discuss the basic properties that a query-level loss function should have and propose a query-level loss function based on the cosine similarity between a ranking list and the corresponding ground truth. We further design a coordinate descent algorithm, referred to as RankCosine, which utilizes the proposed loss function to create a generalized additive ranking model. We also discuss whether the loss functions of existing ranking algorithms can be extended to query-level. Experimental results on the datasets of TREC web track, OHSUMED, and a commercial web search engine show that with the use of the proposed querylevel loss function we can significantly improve ranking accuracies. Furthermore, we found that it is difficult to extend the document-level loss functions to query-level loss functions.

Learning to rank from relevance judgment is an active research area. Itemwise score regression, pairwise preference satisfaction, and listwise structured learning are the major techniques in use. Listwise structured learning has been applied recently to optimize important non-decomposable ranking criteria like AUC (area under ROC curve) and MAP (mean average precision). We propose new, almost-lineartime algorithms to optimize for two other criteria widely used to evaluate search systems: MRR (mean reciprocal rank) and NDCG (normalized discounted cumulative gain) in the max-margin structured learning framework. We also demonstrate that, for different ranking criteria, one may need to use different feature maps. Search applications should not be optimized in favor of a single criterion, because they need to cater to a variety of queries. E.g., MRR is best for navigational queries, while NDCG is best for informational queries. A key contribution of this paper is to fold multiple ranking loss functions into a multi-criteria max-margin optimization. The result is a single, robust ranking model that is close to the best accuracy of learners trained on individual criteria. In fact, experiments over the popular LETOR and TREC data sets show that, contrary to conventional wisdom, a test criterion is often not best served by training with the same individual criterion.

Learning to rank is a new statistical learning technology on creating a ranking model for sorting objects. The technology has been successfully applied to web search, and is becoming one of the key machineries for building search engines. Existing approaches to learning to rank, however, did not consider the cases in which there exists relationship between the objects to be ranked, despite of the fact that such situations are very common in practice. For example, in web search, given a query certain relationships usually exist among the the retrieved documents, e.g., URL hierarchy, similarity, etc., and sometimes it is necessary to utilize the information in ranking of the documents. This paper addresses the issue and formulates it as a novel learning problem, referred to as, ‘learning to rank relational objects’. In the new learning

One of the central issues in learning to rank for information retrieval is to develop algorithms that construct ranking models by directly optimizing evaluation measures used in information retrieval such as Mean Average Precision (MAP) and Normalized Discounted Cumulative Gain (NDCG). Several such algorithms including SVM map and AdaRank have been proposed and their effectiveness has been verified. However, the relationships between the algorithms are not clear, and furthermore no comparisons have been conducted between them. In this paper, we conduct a study on the approach of directly optimizing evaluation measures in learning to rank for Information Retrieval (IR). We focus on the methods that minimize loss functions upper bounding the basic loss function defined on the IR measures. We first provide a general framework for the study and analyze the existing algorithms of SVM map and AdaRank within the framework. The framework is based on upper bound analysis and two types of upper bounds are discussed. Moreover, we show that we can derive new algorithms on the basis of this analysis and create one example algorithm called PermuRank. We have also conducted comparisons between SVM map, AdaRank, PermuRank, and conventional methods of Ranking SVM and Rank-Boost, using benchmark datasets. Experimental results show that the methods based on direct optimization of evaluation measures can always outperform conventional methods of Ranking SVM and RankBoost. However, no significant difference exists among the performances of the direct optimization methods themselves.

LETOR is a benchmark collection for the research on learning to rank for information retrieval, released by Microsoft Research Asia. In this paper, we describe the details of the LETOR collection and show how it can be used in different kinds of researches. Specifically, we describe how the document corpora and query sets in LETOR are selected, how the documents are sampled, how the learning features and meta information are extracted, and how the datasets are partitioned for comprehensive evaluation. We then compare several state-of-the-art learning to rank algorithms on LETOR, report their ranking performances, and make discussions on the results. After that, we discuss possible new research topics that can be supported by LETOR, in addition to algorithm comparison. We hope that this paper can help people to gain deeper understanding of LETOR, and enable more interesting research projects on learning to rank and related topics.

In web search, recency ranking refers to ranking documents by relevance which takes freshness into account. In this paper, we propose a retrieval system which automatically detects and responds to recency sensitive queries. The system detects recency sensitive queries using a high precision classifier. The system responds to recency sensitive queries by using a machine learned ranking model trained for such queries. We use multiple recency features to provide temporal evidence which effectively represents document recency. Furthermore, we propose several training methodologies important for training recency sensitive rankers. Finally, we develop new evaluation metrics for recency sensitive queries. Our experiments demonstrate the efficacy of the proposed approaches.

We offer a simple, effective, and scalable method for statistical machine translation parameter tuning based on the pairwise approach to ranking (Herbrich et al., 1999). Unlike the popular MERT algorithm (Och, 2003), our pairwise ranking optimization (PRO) method is not limited to a handful of parameters and can easily handle systems with thousands of features. Moreover, unlike recent approaches built upon the MIRA algorithm of Crammer and Singer (2003) (Watanabe et al., 2007; Chiang et al., 2008b), PRO is easy to implement. It uses off-the-shelf linear binary classifier software and can be built on top of an existing MERT framework in a matter of hours. We establish PRO’s scalability and effectiveness by comparing it to MERT and MIRA and demonstrate parity on both phrase-based and syntax-based systems in a variety of language pairs, using large scale data scenarios. 1

Abstract. We present a class of models that are discriminatively trained to directly map from the word content in a query-document or documentdocument pair to a ranking score. Like Latent Semantic Indexing (LSI), our models take account of correlations between words (synonymy, polysemy). However, unlike LSI our models are trained with a supervised signal directly on the task of interest, which we argue is the reason for our superior results. We provide an empirical study on Wikipedia documents, using the links to define document-document or query-document pairs, where we obtain state-of-the-art performance using our method. Key words: supervised, semantic indexing, document ranking 1