Revisiting the cluster-based paradigm for implicit search result diversification

To cope with ambiguous and/or underspecified queries, search result diversification (SRD) is a key technique that has attracted a lot of attention. This paper focuses on implicit SRD, where the subtopics underlying a query are unknown. Many existing methods appeal to the greedy strategy for generating diversified results. A common practice is using a heuristic criterion for making the locally optimal choice at each round. As a result, it is difficult to know whether the failures are caused by the optimization criterion or the setting of parameters. Different from previous studies, we formulate implicit SRD as a process of selecting and ranking k exemplar documents through integer linear programming (ILP). The key idea is that: for a specific query, we expect to maximize the overall relevance of the k exemplar documents. Meanwhile, we wish to maximize the representativeness of the selected exemplar documents with respect to the non-selected documents. Intuitively, if the selected exemplar documents concisely represent the entire set of documents, the novelty and diversity will naturally arise. Moreover, we propose two approaches ILP4ID (Integer Linear Programming for Implicit SRD) and AP4ID (Affinity Propagation for Implicit SRD) for solving the proposed formulation of implicit SRD. In particular, ILP4ID appeals to the strategy of bound-and-branch and is able to obtain the optimal solution. AP4ID being an approximate method transforms the target problem as a maximum-a-posteriori inference problem, and the message passing algorithm is adopted to find the solution. Furthermore, we investigate the differences and connections between the proposed models and prior models by casting them as different variants of the cluster-based paradigm for implicit SRD. To validate the effectiveness and efficiency of the proposed approaches, we conduct a series of experiments on four benchmark TREC diversity collections. The experimental results demonstrate that: (1) The proposed methods, especially ILP4ID, can achieve substantially improved performance over the state-of-the-art unsupervised methods for implicit SRD. (2) The initial runs, the number of input documents, query types, the ways of computing document similarity, the pre-defined cluster number and the optimization algorithm significantly affect the performance of diversification models. Careful examinations of these factors are highly recommended in the development of implicit SRD methods. Based on the in-depth study of different types of methods for implicit SRD, we provide additional insight into the cluster-based paradigm for implicit SRD. In particular, how the methods relying on greedy strategies impact the performance of implicit SRD, and how a particular diversification model should be fine-tuned.     

Making Sense of Number Words and Arabic Digits: Does Order Count More?

The ability to choose the larger between two numbers reflects a mature understanding of the magnitude associated with numerical symbols. The present study explores how the knowledge of the number sequence and memory capacity (verbal and visuospatial) relate to number comparison skills while controlling for cardinal knowledge. Preschool children’s (N = 140, M_{age-in-months} = 58.9, range = 41–75) knowledge of the directional property of the counting list as well as the spatial mapping of digits on the visual line were assessed. The ability to order digits on the visual line mediated the relation between memory capacity and number comparison skills while controlling for cardinal knowledge. Beyond cardinality, the knowledge of the (spatial) order of numbers marks the understanding of the magnitude associated with numbers.     

Graph-based term weighting for information retrieval

A standard approach to Information Retrieval (IR) is to model text as a bag of words. Alternatively, text can be modelled as a graph, whose vertices represent words, and whose edges represent relations between the words, defined on the basis of any meaningful statistical or linguistic relation. Given such a text graph, graph theoretic computations can be applied to measure various properties of the graph, and hence of the text. This work explores the usefulness of such graph-based text representations for IR. Specifically, we propose a principled graph-theoretic approach of (1) computing term weights and (2) integrating discourse aspects into retrieval. Given a text graph, whose vertices denote terms linked by co-occurrence and grammatical modification, we use graph ranking computations (e.g. PageRank Page et al. in The pagerank citation ranking: Bringing order to the Web. Technical report, Stanford Digital Library Technologies Project, 1998) to derive weights for each vertex, i.e. term weights, which we use to rank documents against queries. We reason that our graph-based term weights do not necessarily need to be normalised by document length (unlike existing term weights) because they are already scaled by their graph-ranking computation. This is a departure from existing IR ranking functions, and we experimentally show that it performs comparably to a tuned ranking baseline, such as BM25 (Robertson et al. in NIST Special Publication 500-236: TREC-4, 1995). In addition, we integrate into ranking graph properties, such as the average path length, or clustering coefficient, which represent different aspects of the topology of the graph, and by extension of the document represented as a graph. Integrating such properties into ranking allows us to consider issues such as discourse coherence, flow and density during retrieval. We experimentally show that this type of ranking performs comparably to BM25, and can even outperform it, across different TREC (Voorhees and Harman in TREC: Experiment and evaluation in information retrieval, MIT Press, 2005) datasets and evaluation measures.     

Legitimising populist education in Israel: The role of religion

This article analyses two case studies from the Israeli education system that demonstrate how religious themes and language are used in service of populist politics. First, ‘Being Citizens in Israel’ is the standard high school civics textbook that underwent a major revision in 2015. The second case study focuses on new school programmes that focus on the rebuilding of the Third Jewish temple, and the inclusion of references to the Third Temple in other school subject curricula. Both cases were analysed using Brubaker’s terminology, specifically highlighting elements of majoritarinism, anti-institutionalism and protectionism that are especially relevant to the Israeli case. The majoritarian and protectionist elements are dominant within these cases, and convey a set of transcendental ideals in the name of an imagined collectivity that is conceived as superior, sacred, pure, with a historic mission in a manner that antagonises minorities, liberal sensibilities and democratic principles. The anti-institutionalism element is not explicitly present, yet an implicit contextual presence is discussed.     

Concurrent VR VI schedules: primacy of molar control of preference and molecular control of response rates

In the first condition in Experiment 1, 6 rats were exposed to concurrent variable ratio (VR) 30, variable interval (VI) 30-sec schedules. In the next two conditions, the subjects were exposed to concurrent VI VI schedules and concurrent tandem VI-differential-reinforcement-of-high-rate VI schedules. For the latter conditions, the overall and relative reinforcer rates equaled those in the first condition. Only minor differences appeared in time allocation (a molar measure) across conditions. However, local response rate differences (a molecular measure) appeared between schedule types consistently with the interresponse times these schedules reinforced. In Experiment 2, these findings reappeared when the prior experiment was replicated with 5 subjects, except that the VR schedule was replaced by a VI plus linear feedback schedule. These results suggest that within the context tested, the molar factor of relative reinforcement rate controls preference, whereas the molecular factor of the relation between interresponse times and reinforcer probability controls the local response rate.     

The 2010 Benjamin Franklin Medal in Life Science presented to Peter C. Nowell

Peter Nowell is known for his discovery that a small terminal deletion on chromosome 22 is a consistent feature in leukemic cells from chronic myelogenous leukemia (CML) patients. This was the first direct evidence that a human cancer could be the result of a somatic (chromosomal) mutation, and paved the way for the development of a therapy that now cures 95% of individuals with CML.