排序方式: 共有20条查询结果,搜索用时 46 毫秒
1.
In Information Retrieval, since it is hard to identify users’ information needs, many approaches have been tried to solve
this problem by expanding initial queries and reweighting the terms in the expanded queries using users’ relevance judgments.
Although relevance feedback is most effective when relevance information about retrieved documents is provided by users, it
is not always available. Another solution is to use correlated terms for query expansion. The main problem with this approach
is how to construct the term-term correlations that can be used effectively to improve retrieval performance. In this study,
we try to construct query concepts that denote users’ information needs from a document space, rather than to reformulate initial queries using the term correlations
and/or users’ relevance feedback. To form query concepts, we extract features from each document, and then cluster the features into primitive concepts that are then used to form
query concepts. Experiments are performed on the Associated Press (AP) dataset taken from the TREC collection. The experimental evaluation
shows that our proposed framework called QCM (Query Concept Method) outperforms baseline probabilistic retrieval model on
TREC retrieval. 相似文献
2.
3.
Dustin Hillard Eren Manavoglu Hema Raghavan Chris Leggetter Erick Cantú-Paz Rukmini Iyer 《Information Retrieval》2011,14(3):315-336
The critical task of predicting clicks on search advertisements is typically addressed by learning from historical click data.
When enough history is observed for a given query-ad pair, future clicks can be accurately modeled. However, based on the
empirical distribution of queries, sufficient historical information is unavailable for many query-ad pairs. The sparsity
of data for new and rare queries makes it difficult to accurately estimate clicks for a significant portion of typical search
engine traffic. In this paper we provide analysis to motivate modeling approaches that can reduce the sparsity of the large
space of user search queries. We then propose methods to improve click and relevance models for sponsored search by mining
click behavior for partial user queries. We aggregate click history for individual query words, as well as for phrases extracted
with a CRF model. The new models show significant improvement in clicks and revenue compared to state-of-the-art baselines
trained on several months of query logs. Results are reported on live traffic of a commercial search engine, in addition to
results from offline evaluation. 相似文献
4.
Kalyani Chadha 《Journalism Practice》2016,10(5):608-625
The notion that journalists in an interconnected world increasingly share values typically associated with the so-called “professional model” has gained considerable currency with scholars arguing that ideas such as a belief in journalistic autonomy, public service, objectivity, and the significance of ethics are widely espoused by journalists on a global scale. Underlying this conceptualization is a taken-for-granted assumption regarding the adoption of journalistic values that originated in Western democracies which neglects how they are embraced in non-Western contexts. This paper examines newsroom values in India’s regional television channels, which have emerged as a major news source in the country. Findings indicate that in the case of Indian regional television, local socio-political and economic factors undermine the adoption of professional norms derived from the Anglo-European model by Indian journalists who see such norms as having little functional value or relevance to their work. 相似文献
5.
6.
Raamesh Gowri Raghavan 《Resonance》2005,10(1):17-24
Historical linguistics deals with the evolutionary relationships of languages to one another. Of the many methods of analysis
used in this field, the numerical method ofglottochronology has been useful (as well as controversial) among linguists for its simplistic approach of comparing lists of supposedly ‘core’
(or basic) words between languages, and finding relationships by determining the percentages of cognates between them. Here
I discuss the method with its limitations, and the recent application of sophisticated techniques to overcome them. 相似文献
7.
In terms of international education, the concept of online education seems to be a growing trend. Edxonline.org, Minervaproject.com, and Udacity.com are all new massive online open courses (MOOCs)—education websites similar to Coursera offering students the ability to receive the best education from elite universities entirely online. The most tantalizing promise of a company like Coursera is the role it might play in improving education for the world's have-nots: high school dropouts, the global poor, and those less able to self-teach. 相似文献
8.
The relevance feedback process uses information obtained from a user about a set of initially retrieved documents to improve subsequent search formulations and retrieval performance. In extended Boolean models, the relevance feedback implies not only that new query terms must be identified and re-weighted, but also that the terms must be connected with Boolean And/Or operators properly. Salton et al. proposed a relevance feedback method, called DNF (disjunctive normal form) method, for a well established extended Boolean model. However, this method mainly focuses on generating Boolean queries but does not concern about re-weighting query terms. Also, this method has some problems in generating reformulated Boolean queries. In this study, we investigate the problems of the DNF method and propose a relevance feedback method using hierarchical clustering techniques to solve those problems. We also propose a neural network model in which the term weights used in extended Boolean queries can be adjusted by the users’ relevance feedbacks. 相似文献
9.
Leslie LK Raghavan R Hurley M Zhang J Landsverk J Aarons G 《Child abuse & neglect》2011,35(5):333-342
Objectives
Public Law (P.L.) 110-351, the “Fostering Connections to Success Act,” calls for state child welfare agencies to partner with Medicaid and pediatric experts to provide planning and oversight regarding the provision of health and mental health services, including medication, to children in state custody. Recent reports, media cases, and class action lawsuits suggest over-use of psychotropic medications to address the behavioral needs of children in the child welfare system. We examined geographic variability in psychotropic medication use across US child welfare agency catchment areas to determine how rates of psychotropic medication use vary in relation to child, community, child welfare, and health system-level factors.Methods
Cross-sectional analysis of Wave 1 data for the 92 child welfare catchment areas participating in the National Survey of Child and Adolescent Well-being, a random probability sample of 2,504 children ages 2-15 years undergoing investigation for abuse and neglect. We employed multilevel regression modeling to examine the impact of catchment-level variables on medication use, controlling for child-level variables.Results
Fifteen percent of children reported taking psychotropic medications. Rates of medication use across catchment areas ranged widely from 0 to 40%, a 40-fold difference. On multi-level logistic regression modeling, older age (p < .001), male gender (p < .001), emotional and behavioral problems (p < .001), and insurance (p = .05) were associated with psychotropic medication use at the child-level. At the catchment-level, stressful environment within the child welfare system was negatively associated with medication use. No other catchment-level variables examined were found to explain use.Conclusions
Striking disparities in medication use exist across catchment areas in this national sample. Of the catchment variables examined, only stressful environment was related to medication use.Practice implications
These findings highlight significant geographic variation in medication use that most likely reflect both under-use and over-reliance on psychotropic medication. The link between child welfare environment and medication use suggests the influence of systemic, as opposed to clinical, causes of variation in medication use. This requires greater implementation of organizational processes governing quality of care for this highly vulnerable population. 相似文献10.