K-Extractor: Automatic Knowledge Extraction for Hybrid Question Answering

Balakrishna, Mithun; Werner, Steven; Tatu, Marta; Erekhinskaya, Tatiana; Moldovan, Dan

doi:10.1109/icsc.2016.30

Cited by 6 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this day, several powerful tools have been developed such as automatic knowledge collection systems, knowledge base systems, fuzzy logical elements, genetic algorithms, expert systems based on worked out situations, neural networks, external intelligence technology, etc [176]- [184] that can be used, including in sensor systems for the automatic solution of problems that otherwise would require human participation. These devices or methods have minimal computational complexity and can be implemented in small sensor systems, single sensors, or arrays on simple microcontrollers [185]- [189].…”

Section: E Artificial Intelligencementioning

confidence: 99%

Wireless Sensor Network as a Mesh: Vision and Challenges

et al. 2022

View full text Add to dashboard Cite

Nowadays, network technologies are developing very rapidly. The growing volume of transmitted information (video, data, VoIP, etc.), the physical growth of networks, and inter-network traffic are forcing manufacturers to produce more powerful and ''smart'' devices that use new methods of transferring and sorting data. Such connected smart devices (IoT) are used in intelligently controlled traffic for self-driving vehicles in Vehicle Adhoc Networks (VANET), in electricity and water in smart cities, and in-home automation in smart homes. These types of connected Internet of Things (IoT) devices are used to leverage different types of network structures. Such IoT sensor devices can be deployed as a wireless sensor network (WSN) in a mesh topology. Both WSNs and Wireless Mesh Networks (WMNs) are easy to organize as well as to deploy. In this case, there are many reasons for combining these different types of networks. In particular, the detailed sensory capabilities of sensor networks may be improved by increasing bandwidth, reliability and power consumption in the mesh topology. However, there are currently only a handful of studies devoting to integrate these two different types of networks. In addition, there is no systematic review of existing interconnection methods. That is why in this article we explore the existing methods of these two networks and provide an analytical basis for their relationship. We introduce the definition of WSN and WMN and then look at some case studies. Afterward, we present several challenges and opportunities in the area of combined Wireless Mesh Sensor Network (WMSN) followed by a discussion on this interconnection through literature review and hope that this document will attract the attention of the community and inspire further research in this direction.

show abstract

Section: E Artificial Intelligencementioning

confidence: 99%

Wireless Sensor Network as a Mesh: Vision and Challenges

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Besides the above literature, there are some natural language question/answering systems that pay attention to many other interesting research directions. Sun et al [26], Balakrishna et al [54] and Tatu et al [55] mined answers from integrated structured data and unstructured data. El-Ansari et al [56] presented a Question Answering system that combines multiple knowledge bases.…”

Section: Natural Language Question/answering Without Aggregation Over...mentioning

confidence: 99%

Natural language aggregate query over RDF data

Dang

Yao

et al. 2018

Information Sciences

View full text Add to dashboard Cite

Natural language question/answering over RDF data has received widespread attention. Although there have been several studies that have dealt with a small number of aggregate queries, they have many restrictions (i.e., interactive information, controlled question or query template). 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 mainly 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 or not, which will greatly affect the aggregate result. Finally, we conduct extensive experiments over real datasets (QALD benchmark and DBpedia), and the experimental results demonstrate that our solution is effective.

show abstract

“…Closed-domain QA systems aim to address a specific area of knowledge, providing more accurate answers and being easier to fine tune the system. Some examples of Closed-domain QA are Question Answer System on Education Acts [8], Python Question Answer System (PythonQA) [9], and K-Extractor [2]. Opendomain QA systems attempt to work with any domain of knowledge, having a broader knowledge base than the closed-domain.…”

Section: Related Workmentioning

confidence: 99%