Figure - available from: Cluster Computing
This content is subject to copyright. Terms and conditions apply.
Source publication
Scientific retrieval systems need to be given domain search terms for searching publications, however, as natural language, search terms provided by users are often fuzzy and limited and some relevant terms are always overlooked in searching. Meanwhile, users always desire to be given domain related keywords to enlighten themselves what other terms...
Similar publications
Natural Language Inference (NLI) is fundamental to many Natural Language Processing (NLP) applications including semantic search and question answering. The NLI problem has gained significant attention thanks to the release of large scale, challenging datasets. Present approaches to the problem largely focus on learning-based methods that use only...
Traditional search mechanisms are based on the keyword search, which does not consider the semantic links
between different concepts. This leads to the loss of relevant documents due to inaccurate query formulation
or using contextually close words and concepts in the query. To solve the problems of formulating user queries
and interdisciplinarity...
Content-based recommendation of books and other media is usually based on semantic similarity measures. While metadata can be compared easily, measuring the semantic similarity of narrative literature is challenging. Keyword-based approaches are biased to retrieve books of the same series or do not retrieve any results at all in sparser libraries....
Entity linking is the task of mapping potentially ambiguous terms in text to their constituent entities in a knowledge base like Wikipedia. This is useful for organizing content, extracting structured data from textual documents, and in machine learning relevance applications like semantic search, knowledge graph construction, and question answerin...
Citations
... Several different approaches have recently been proposed in order to increase the accuracy of the predicted ratings. Also there is a lot of interest for the application of RS in such area as movies [29,32], music [33], news [34,35], tourism [36,37], social networks [38,39], scientific papers [40,41] and etc. [42][43][44][45][46]. ...
Collaborative filtering which is the most successful technique of the Recommender System, has recently attracted great attention, especially in the field of e-commerce. CF is used to help users find their preferred items by assessing the preferences of other users to find most similar to the active one. Sparse datasets defend the efficiency of CF. Therefore this paper proposes two new methods that use the information provided via user ratings to overcome the sparsity problem without any change of dimension. The methods are implemented via Map-Reduce clustering-based CF. The proposed approaches have been tested by Movielens 100K, Movielens 1M, Movielens 20M, and Jester datasets in order to make a comparison with the traditional techniques. The experimental results show that the proposed methods can lead to improved performance of the Recommender System.
... The proposal modeled bilingual document in English and Chinese to search semantic information in English and Chinese language through topic words. [2,34] proposed a concept based recommender system for scientific paper retrieval. The concepts are extracted from keywords included in user's query. ...
Information retrieval systems strive for catering user’s information need in terms of providing most relevant documents with regards to user’s query. Despite of decades of research in information retrieval field, users still struggle to meet their information need. There are two major challenges for information retrieval systems. First, vagueness in specifying user’s information need through query. Second, lack of effective methods to perform partial match between documents and query. In this work, Bayesian Rough Set based intelligent information retrieval model is proposed, which combines rough set theory and Bayesian reasoning. Both, user queries and web pages are presented in the form of rough sets. The approximation regions for query and documents are calculated using Bayesian Rough Set Model. Proposed model exploits rough relations for relevance ranking of web pages. Initial results of the proposed model are presented and demonstrate better performance than some of existing models.
Business model innovation consists of new ways of defining, creating, and capturing value including non-monetary value, and is an indicator of crossing traditional sector boundaries, thereby providing the necessary agency to achieve significant new market opportunities around technological innovation. Individual businesses may lack the scope or depth of competencies required, especially in the case of entrenched industrial structures, framings, regulatory provision, and consumer attitudes. Business models are thus potentially ossified within highly structured socio-technical systems. This article analyses innovation in business models arising from the confluence of two mature and stable industries under conditions of external pressure, deregulation, privatisation, and the emergence of a new, shared interest. We illustrate the paper with examples of vehicle manufacturers developing business concepts for vehicle-to-grid, domestic energy, second life, and industrial electricity provision from renewable energy. We find that in the period 2012 to 2020, 17 vehicle manufacturers used 38 electric models to test a diverse menu of options established from four applications with changes in boundary conditions that have influenced business model innovation. This process created space for energy policy and mobility policy to become increasingly intertwined as battery electric vehicles enter the mass market, raising questions over the future of automobility as well as electricity generation and distribution.
Classical or traditional Information Retrieval (IR) approaches rely on the word-based representations of query and documents in the collection. The specification of the user information need is completely based on words figuring in the original query in order to retrieve documents containing those words. Such approaches have been limited due to the absence of relevant keywords as well as the term variation in documents and user’s query. The purpose of this paper is to present a new method to Semantic Information Retrieval (SIR) to solve the limitations of existing approaches. Concretely, we propose a novel method SIRWWO (Semantic Information Retrieval using Wikipedia, WordNet, and domain Ontologies) for SIR by combining multiple knowledge sources Wikipedia, WordNet, and Description Logic (DL) ontologies. In order to illustrate the approach SIRWWO, we first present the notion of Labeled Dynamic Semantic Network (LDSN) by extending the notions of dynamic semantic network and extended semantic net based on WordNet (and DAML ontology library). According to the notion of LDSN, we obtain the notion of Weighted Dynamic Semantic Network (WDSN, intuitively, each edge in WDSN is assigned to a number in the [0, 1] interval) and give the WDSN construction method using Wikipedia, WordNet, and DL ontology. We then propose a novel metric to measure the semantic relatedness between concepts based on WDSN. Lastly, we investigate the approach SIRWWO by using semantic relatedness between users’ query keywords and digital documents. The experimental results show that our proposals obtain comparable and better performance results than other traditional IR system Lucene.
