We describe a framework for Adaptive Multilingual Information Retrieval (AMIR) which allows multilingual resource discovery and delivery using on-the-fly machine translation of documents and queries. Result documents ...
详细信息
We present a language independent approach for conflation that does not depend on predefined rules or prior knowledge of the target language. The proposed unsupervised method is based on an enhancement of the pure n-g...
详细信息
We present a language independent approach for conflation that does not depend on predefined rules or prior knowledge of the target language. The proposed unsupervised method is based on an enhancement of the pure n-gram model that is used to group related words based on a revised string-similarity measure. In order to detect and eliminate terms that are created by this process, but that are most likely not relevant for the query (”noisy terms”), an approach based on mutual information scores computed based on web statistical cooccurrences data is proposed. Furthermore, an evaluation of this approach is presented.
Providers of products and services are faced with the dual challenge of supporting the languages and individual needs of the global customer while also accommodating the increasing relevance of user-generated content....
详细信息
Providers of products and services are faced with the dual challenge of supporting the languages and individual needs of the global customer while also accommodating the increasing relevance of user-generated content. As a result, the content and localisation industries must now evolve rapidly from manually processing predicable content which arrives in large jobs to the highly automated processing of streams of fast moving, heterogeneous and unpredictable content. This requires a new generation of digital content management technologies that combine the agile flow of content from developers to localisers and consumers with the data-driven language technologies needed to handle the volume of content required to feed the demands of global markets. data-driven technologies such as statistical machine translation, cross-lingual information retrieval, sentiment analysis and automatic speech recognition, all rely on high quality training content, which in turn must be continually harvested based on the human quality judgments made across the end-to-end content processing flow. This paper presents the motivation, approach and initial semantic models of a collection of research demonstrators where they represent a part of, or a step towards, documenting in a semantic model the multi-lingual semantic web.
Integrating and relating heterogeneous data using inference is one of the cornerstones of semantic technologies and there are a variety of ways in which this may be achieved. Cross source relationships can be automati...
详细信息
Drawing on the experiences and context of others who have already used a particular resource can greatly facilitate that resource's reuse. Such reuse is essential when the resources in question are digital learnin...
详细信息
Drawing on the experiences and context of others who have already used a particular resource can greatly facilitate that resource's reuse. Such reuse is essential when the resources in question are digital learning assets, services and models which are expensive both in terms of time and monetary expenditure to develop and use. When these resources are deployed in personalised settings, where each user may be delivered a tailored sequence of resources that uniquely suits their particular needs, gathering and federating a rich view of how these resources are being used becomes important. In this article we describe an approach to facilitating the federating of contextual usage data, which is compiled over the life cycle of a resource. Given that this data is likely to come from a range of different sources, our approach will need to be able to cope with the high level of heterogeneity expected in terms of its structure, syntax and semantics. We describe how such data may be used to support users in assessing the value of learning resources and facilitating their appropriate reuse.
Existing approaches for selecting the most appropriate reasoner for different semantic applications mainly relies on discussions between application developers and reasoner experts. However this approach will become i...
详细信息
Existing approaches for selecting the most appropriate reasoner for different semantic applications mainly relies on discussions between application developers and reasoner experts. However this approach will become inadequate with the increasing adoption of Semantic Web technologies in applications from different domains and the rapid development of OWL reasoning technologies. This work proposes RESP, a computer aided reasoner selection process designed to perform reasoner selection for different applications and so reduce the effort and communication overhead required to select the most appropriate reasoner. Preliminary evaluation results show that RESP successfully helps application developers to select the most appropriate reasoner, or at least narrow down the number of candidate reasoners to consider. Contributions of this work are two folds: (1) the design of a (relatively simple but useful) computer aided OWL reasoner selection process, and (2) the identification and discussion of a set of example application characteristics that can affect the OWL reasoner selection.
Recommendation algorithms and multi-class classifiers can support users of social bookmarking systems in assigning tags to their bookmarks. Content based recommenders are the usual approach for facing the cold start p...
详细信息
Integration of disparate information resources has long been a significant research topic. Semantic approaches can help by allowing expression of concepts divorced from syntax and allowing rich, structured meta-data t...
详细信息
ISBN:
(纸本)9781424492190
Integration of disparate information resources has long been a significant research topic. Semantic approaches can help by allowing expression of concepts divorced from syntax and allowing rich, structured meta-data to be published in a form that is amenable to machine processing, reasoning and inter-domain concept mapping. However the creation of mappings, especially in a dynamic federations of autonomous entities, is time-consuming and vulnerable to brittleness and high maintenance costs due to change at many levels in the system. In this paper we propose an approach to managing change and maximizing mapping reuse by building explicit models of the federal relationship context of mapping deployment. These descriptions enable automated support for mapping reuse suggestions and ease discovery of relevant mappings due to changes at the federation, peer domain, shared capability or local model levels.
Policy engineering is the process of authoring IT management policies, detecting and resolving policy conflicts and revising existing policies to accommodate changing IT resources, business goals and business processe...
详细信息
ISBN:
(纸本)9781424492190
Policy engineering is the process of authoring IT management policies, detecting and resolving policy conflicts and revising existing policies to accommodate changing IT resources, business goals and business processes. Policy authoring is often followed by policy enforcement where the actions specified by subjects are performed on targets (resources). In this paper, we study the use of semantically enhanced techniques, such as ontologies, to model resources and their corresponding actions, coupled with a mechanism that can accommodate frequent organizational change, to model policy subjects. For the modeling of policy subjects, the rule-based Community-based Policy management will be used. This integration falls into the category of combining Description Logics (DL) and Logic Programs (LP). We aim to study this integration primarily from the scope of overall system expressivity, but also from the scope of minimizing the cognitive load perceived by policy authors. Such an evaluation can help determine shortfalls in the design of the software system or of the policy model used. To study the balance in modeling with DL and LP techniques, the encoding of part of the Trinity College Dublin statutes will be performed, which is a sufficiently complex real-world example.
Integrating and relating heterogeneous data using inference is one of the cornerstones of semantic technologies and there are a variety of ways in which this may be achieved. Cross source relationships can be automati...
详细信息
Integrating and relating heterogeneous data using inference is one of the cornerstones of semantic technologies and there are a variety of ways in which this may be achieved. Cross source relationships can be automatically translated or inferred using the axioms of RDFS/OWL, via user generated rules, or as the result of SPARQL query result transformations. For a given problem it is not always obvious which approach (or combination of approaches) will be the most effective and few guidelines exist for making this choice. This paper discusses these three approaches and demonstrates them using an "acquaintance" relationship drawn from data residing in common RDF information sources such as FOAF and DBLP data stores. The implementation of each approach is described along with practical considerations for their use. Quantitative and qualitative evaluation results of each approach are presented and the paper concludes with initial suggestions for guiding principles to help in selecting an appropriate approach for integrating heterogeneous semantic data sources.
暂无评论