In this paper, we present a general learning framework which treats the ranking problem for various Information Retrieval tasks. We extend the training set generalization error bound proposed by [4] to the ranking case and show that the use of unlabeled data can be beneficial for learning a ranking function. We finally discuss open issues regarding the use of the unlabeled data during training ...

Web search quality can vary widely across languages, even for the same information need. We propose to exploit this variation in quality by learning a ranking function on bilingual queries: queries that appear in query logs for two languages but represent equivalent search interests. For a given bilingual query, along with corresponding monolingual query log and monolingual ranking, we generate...

In this paper we present an approach to score aggregation for specialized search systems. In our work we focus on document ranking in scientific publication databases. We work with the collection of scientific publications of the CERN Document Server. This paper reports on work in progress and describes rank aggregation framework with score normalization. We present results that we obtained wit...

We study the consistency of listwise ranking methods with respect to the popular Normalized Discounted Cumulative Gain (NDCG) criterion. State of the art listwise approaches replace NDCG with a surrogate loss that is easier to optimize. We characterize NDCG consistency of surrogate losses to discover a surprising fact: several commonly used surrogates are NDCG inconsistent. We then show how to ...

Existing approaches on XML keyword search mostly focus on querying over single data source. However, searching over hundreds or even thousands of (distributed) data sources by sequentially querying every single data source is extremely high cost, thus it can be impractical. In this paper, we propose an approach for selecting top-k data sources to a given query in order to avoid high cost of sea...

Suppose all the individuals in a field are linearly ordered. Groups of individuals form teams. Is there a perfect ranking function of each team based on the members of the team? We prove that under a very mild and reasonable set of axioms for the ranking function, no such ranking function exists. AMS Subject Classification: 68R05, 91F10, 06A05, 06A07.

Much progress has been made in the English question-answering task since it was initiated in TREC-8 and our last participation in TREC-2001. QA is a complex semantics-oriented task, and it is necessary that much linguistic processing, auxiliary resources, and learning steps are needed to come up with adequate performance to the task [1]. Chinese language factoid QA was first introduced during N...

Distributions over rankings are used to model data in various settings such as preference analysis and political elections. The factorial size of the space of rankings, however, typically forces one to make structural assumptions, such as smoothness, sparsity, or probabilistic independence about these underlying distributions. We approach the modeling problem from the computational principle th...

Traditional mechanisms used to rank learning objects are not longer viable thanks to the current abundance of resources. This work proposes the construction of an improved relevance ranking function based on contextualized attention data extracted from the interaction between the users and the objects. A multidimensional approach to relevance is followed. Beside the Algorithmic relevance, curre...

This paper presents an indexing technique based on WordNet synonyms and holonyms. This technique has been developed for the Geographical Information Retrieval task. It may help in finding implicit geographic information contained in texts, particularly if the indication of the containing geographical entity is omitted. Our experiments were carried out with the Lucene search engine over the GeoC...