We tackle the computational problem of query-conditioned search. Given a machine-learned scoring rule and a query distribution, we build a predictive index by precomputing lists of potential results sorted based on an expected score of the result over future queries. The predictive index datastructure supports an anytime algorithm for approximate retrieval of the top elements. The general approach is applicable to webpage ranking, internet advertisement, and approximate nearest neighbor search. It is particularly effective in settings where standard techniques (e.g., inverted indices) are intractable. We experimentally find substantial improvement over existing methods for internet advertisement and approximate nearest neighbors.

Query expansion is a long-studied approach for improving retrieval effectiveness by enhancing the user's original query with additional related words. Current algorithms for automatic query expansion can often improve retrieval accuracy on average, but are not robust: that is, they are highly unstable and have poor worst-case performance for individual queries. To address this problem, we introduce anovel formulation of query expansion as a convex optimization problem over a word graph. The model combines initial weights from a baseline feedback algorithmwith edge weights based on word similarity, and integrates simple constraints to enforce set-based criteria such as aspect balance, aspect coverage, and term centrality. Results across multiple standard test collections show consistent andsignificant reductions in the number and magnitude of expansion failures, while retaining the strong positive gains of the baseline algorithm. Our approach does not assume a particular retrieval model, making it applicable to a broad class of existing expansion algorithms.

This paper studies global ranking problem by learning to rank methods. Conventional learning to rank methods are usually designed for `local ranking', in the sense that the ranking model is defined on a single object, for example, a document in information retrieval. For many applications, this is a very loose approximation. Relations always exist between objects and it is better to define the ranking model as a function on all the objects to be ranked (i.e., the relations are also included). This paper refers to the problem as global ranking and proposes employing a Continuous Conditional Random Fields (CRF) for conducting the learning task. The Continuous CRF model is defined as a conditional probability distribution over ranking scores of objects conditioned on the objects. It can naturally represent the content information of objects as well as the relation information between objects, necessary for global ranking. Taking two specific information retrieval tasks as examples, the paper shows how the Continuous CRF method can perform global ranking better than baselines.

We present a class of nonlinear (polynomial) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score. Dealing with polynomial models on word features is computationally challenging. We propose a low rank (but diagonal preserving) representation of our polynomial models to induce feasible memory and computation requirements. We provide an empirical study on retrieval tasks based on Wikipedia documents, where we obtain state-of-the-art performance while providing realistically scalable methods.

In this paper, we propose causality as a unified framework to explain query answers and non-answers, thus generalizing and extending several previously proposed approaches of provenance and missing query result explanations. We develop our framework starting from the well-studied definition of actual causes by Halpern and Pearl. After identifying some undesirable characteristics of the original definition, we propose functional causes as a refined definition of causality with several desirable properties. These properties allow us to apply our notion of causality in a database context and apply it uniformly to define the causes of query results and their individual contributions in several ways: (i) we can model both provenance as well as non-answers, (ii) we can define explanations as either data in the input relations or relational operations in a query plan, and (iii) we can give graded degrees of responsibility to individual causes, thus allowing us to rank causes. In particular, our approach allows us to explain contributions to relational aggregate functions and to rank causes according to their respective responsibilities. We give complexity results and describe polynomial algorithms for evaluating causality in tractable cases. Throughout the paper, we illustrate the applicability of our framework with several examples. Overall, we develop in this paper the theoretical foundations of causality theory in a database context.

Introduction In the last years, many useful NLP tools have been developed and many of them are now even available commercially. Most of these tools are monolingual or multi-monolingual, meaning that the software can deal with more than one language, but that the re sults will al ways be displayed in the same language as the text. We therefore distinguish these applications from cross-lingual software, which is software that helps to transgress the language bound ary. Examples for such applications are machine translation and cross-lingual document retrieval, i.e. retrieval using search engines which allow to en ter a search term in one language and which also yield results in other languages, usually because the query is translated in one way or another. In our eyes, cross-lingual applications are currently the bottleneck of available NLP tools. To our knowledge, there are no applications that allow comparing documents written in dif ferent languages with each other and there are very few which give users a quick overview of the ap proximate contents of documents written in different languages.

In this paper, our aim is to propose a model that helps in the efficient use of an information system by users, within the organization represented by the IS, in order to resolve their decisional problems. In other words we want to aid the user within an organization in obtaining the information that corresponds to his needs (informational needs that result from his decisional problems). This type of information system is what we refer to as economic intelligence system because of its support for economic intelligence processes of the organisation. Our assumption is that every EI process begins with the identification of the decisional problem which is translated into an informational need. This need is then translated into one or many information search problems (ISP). We also assumed that an ISP is expressed in terms of the user's expectations and that these expectations determine the activities or the behaviors of the user, when he/she uses an IS. The model we are proposing is used for the conception of the IS so that the process of retrieving of solution(s) or the responses given by the system to an ISP is based on these behaviours and correspond to the needs of the user.

The quality of the ranking function is an important factor that determines the quality of the Information Retrieval system. Each document is assigned a score by the ranking function; the score indicates the likelihood of relevance of the document given a query. In the vector space model, the ranking function is defined by a mathematic expression. We propose a fuzzy logic (FL) approach to defining the ranking function. FL provides a convenient way of converting knowledge expressed in a natural language into fuzzy logic rules. The resulting ranking function could be easily viewed, extended, and verified: * if (tf is high) and (idf is high) > (relevance is high); * if (overlap is high) > (relevance is high). By using above FL rules, we are able to achieve performance approximately equal to the state of the art search engine Apache Lucene (deltaP10 +0.92%; deltaMAP -0.1%). The fuzzy logic approach allows combining the logic-based model with the vector model. The resulting model possesses simplicity and formalism of the logic based model, and the flexibility and performance of the vector model.

Clickthrough data is a particularly inexpensive and plentiful resource to obtain implicit relevance feedback for improving and personalizing search engines. However, it is well known that the probability of a user clicking on a result is strongly biased toward documents presented higher in the result set irrespective of relevance. We introduce a simple method to modify the presentation of search results that provably gives relevance judgments that are unaffected by presentation bias under reasonable assumptions. We validate this property of the training data in interactive real world experiments. Finally, we show that using these unbiased relevance judgments learning methods can be guaranteed to converge to an ideal ranking given sufficient data.

This paper evaluates the robustness of learning from implicit feedback in web search. In particular, we create a model of user behavior by drawing upon user studies in laboratory and real-world settings. The model is used to understand the effect of user behavior on the performance of a learning algorithm for ranked retrieval. We explore a wide range of possible user behaviors and find that learning from implicit feedback can be surprisingly robust. This complements previous results that demonstrated our algorithm's effectiveness in a real-world search engine application.