In this article we describe the Oslo University College’s participation in the INEX 2009 Book track. This year’s tasks have been featuring complex topics, containing aspects. These lend themselves to use in both the book retrieval and the focused retrieval tasks. The OUC has submitted retrieval results for both tasks, focusing on using the Wikipedia texts for query expansion, as well as utilizi...

This paper presents our work towards a novel approach for Quality Estimation (QE) of machine translation based on sequences of adjacent words, the so-called phrases. This new level of QE aims to provide a natural balance between QE at word and sentence-level, which are either too fine grained or too coarse levels for some applications. However, phrase-level QE implies an intrinsic challenge: ho...

........................................................................................................................ xxi

Одна из основных задач информационного поиска—извлечение документов, релевантных информационной потребности пользователя, выраженной запросом. Зачастую пользовательские запросы не превосходят 3 слов, что усложняет задачу. Многочисленные исследования показали, что автоматическое расширение запроса в среднем повышает точность, несмотря на то, что для некоторых запросов результаты ухудшаются. В ст...

The problem to decide whether a given multivariate (quasi-)rational function has only positive coefficients in its power series expansion has a long history. It dates back to Szegö [10], who showed that ((1−Z1)(1−Z2) + (1−Z1)(1−Z3) + (1−Z2)(1−Z3)) for β ≥ 1/2 is positive, in the sense that all its series coefficients are positive, using an involved theory of special functions. In contrast to th...

Document type: Journal: Volume: Number: Pages: Additional material: Language: 2 documents’ titles. This is illustrated by the excerpt from a result list which is presented in Figure 41. Figure 41: Excerpt from a result list In the result list, the document titles were interlinked with the respective metadata pages of the documents. Amongst others, these pages presented the following information...

In this paper, we describe the search system, developed at Ghent University for the TREC 2012 Microblog Track in order to rank Twitter messages or ‘tweets’ from a fixed corpus in response to a number of search requests. Our system ranks the tweets based on a Logistic Regression classifier trained with data from the Microblog Track 2011. The features used for training the classifier include loca...

The 2016 CLEF eHealth Task 3 aims to evaluation the effectiveness of information retrieval systems when searching for health content on the web. The ClueWeb12 B13 data set is utilized in this task. This paper presents our work on the 2016 CLEF eHealth Task 3. We propose a Web-based query expansion method and a combination method to better understand and satisfy the task. In particular, we test ...

For this first participation to the CHiC Lab, we focused on understanding the challenges of working with a collection of cultural heritage objects with short textual descriptions and on how to fine-tune a set of weighting models from the probability models based on Divergence From Randomness to perform uniformly in monolingual and multilingual scenarios. The official runs submitted used PL2 as ...