Search

• A formal definition for crowdsourcing listing item task was presented. • An incentive mechanism was proposed for the listing item task. • The mechanism was proved to be efficient both theoretically and experimentally. Crowdsourcing is a new strategy of leveraging intelligence from a large number of workers to complete tasks. An incentive mechanism is an effective way for improving the quality of answers in crowdsourcing. However, a special but common type of crowdsourcing task, called listing item task, has not been fully investigated. In this paper, we focus on the incentive mechanism for this listing item task. In particular, we first provide a formal definition of this task. Then, we propose an effective incentive mechanism considering both the precision and recall of the answers. Next, we prove that the proposed mechanism is incentive-compatible and satisfies no free lunch criterion. Finally, we conduct a series of experiments on our crowdsourcing platform CrowdKnow and a public platform ZhiDao. The experimental results demonstrate that our incentive mechanism achieves a remarkable improvement for listing item tasks compared with other related mechanisms. [ABSTRACT FROM AUTHOR]

Natural language question/answering over RDF (Resource Description Framework) data has received widespread attention. Although several studies can address a small number of aggregate queries, these studies have many restrictions (e.g., interactive information, controlled questions or query templates). Thus far, there has been no natural language querying mechanism that can process general aggregate queries over RDF data. Therefore, we propose a framework called NLAQ (Natural Language Aggregate Query). First, we propose a novel algorithm to automatically understand a user's query intention, which primarily contains semantic relations and aggregations. Second, to build a better bridge between the query intention and RDF data, we propose an extended paraphrase dictionary ED to obtain more candidate mappings for semantic relations, and we introduce a predicate-type adjacent set PT to filter out inappropriate candidate mapping combinations in semantic relations and basic graph patterns. Third, we design a suitable translation plan for each aggregate category and effectively distinguish whether an aggregate item is numeric, which will greatly affect the aggregate result. Finally, we conduct extensive experiments over real datasets (QALD benchmark and DBpedia). The experimental results demonstrate that our solution is effective. [ABSTRACT FROM AUTHOR]