DBpedia and YAGO Based System for Answering Questions in Natural Language

Boiński, Tomasz; Szymański, Julian; Dudek, Bartłomiej; Zalewski, P.; Dompke, Szymon; Czarnecka, Maria

doi:10.1007/978-3-319-98443-8_35

Cited by 3 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the growing interest in semantic resources, several recent approaches have been proposed for semantically analysing user queries and matching them at a semantics-based level to their related documents. However, these approaches either use a single semantic resource such as Lu et al (2015), , Han et al (2016), Selmi et al (2018), Boiński et al (2018) and Royo et al (2005) or multiple heterogeneous semantic resources such as Maree et al (2016), Vigneshwari and Aramudhan (2015), Shen and Lee (2018), Kmail et al (2015), Zhu and Iglesias (2018), Goldfarb and Le Franc (2017) and Wimalasuriya and Dou (2009). For instance, the system proposed in Royo et al (2005) maps query keywords to their corresponding synsets in WordNet ontology.…”

Section: Related Workmentioning

confidence: 99%

“…As acknowledged by the authors, exploiting WordNet only is not sufficient and therefore they planned to combine additional ontologies to maximise the depth and breadth of domain coverage. Similarly, the systems proposed in Lu et al (2015), Han et al (2016), Selmi et al (2018), Boiński et al (2018) and Royo et al (2005) exploited single ontologies such as FrameNet, VerbNet and MESH to tackle the issue of semantically interpreting user queries and match them to their relevant documents. However, as reported in Maree and Belkhatir (2015), the domain coverage of these ontologies is limited and is not frequently updated; leading to significantly degrading the quality of the produced results by such systems.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Semantics-based key concepts identification for documents indexing and retrieval on the web

Maree

2021

IJICA

View full text Add to dashboard Cite

Bridging the semantic gap on the web remains one of the crucial challenges for current horizontal and domain-specific information retrieval systems. This challenge becomes even more pronounced when users express their information needs using short queries that are formulated using a few number of keywords, therefore relying on keywords for indexing web documents results in degrading the quality of the returned results. In this article, we introduce an approach that employs knowledge captured by large-scale knowledge resources to identify key query terms and retrieve semantically-relevant documents. In this context, key terms are mapped to their semantic correspondences and variable term weights are assigned based on the semantic and taxonomic relations for each term. To demonstrate the effectiveness of the proposed approach, we have conducted experimental evaluation using Glasgow's NPL test collections. Findings indicate that the effectiveness has improved against four conventional similarity metrics that are based on the bag-of-words similarity model.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Semantics-based key concepts identification for documents indexing and retrieval on the web

Maree

2021

IJICA

View full text Add to dashboard Cite

show abstract

“…Nowadays, the development of artificial intelligence is associated with machine learning [20], neural networks [21], evolutionary computing [22], image recognition [23], natural language processing [24,25], and robotics [26,27]. Moreover, a new multidisciplinary paradigm has been introduced, namely Ambient Intelligence (AmI), combining Norman's so-called Invisible Computer and Ubiquitous Computing [28].…”

Section: Introductionmentioning

confidence: 99%

University Students’ Research on Artificial Intelligence and Knowledge Management. A Review and Report of Multi-case Studies

Owoc

Weichbroth

2021

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Leading technologies are very attractive for students preparing their theses as the completion of their studies. Such an orientation of students connected with professional experiences seems to be a crucial motivator in the research in the management and business areas where these technologies condition the development of professional activities. The goal of the paper is the analysis of students' thesis topics defended in the last 10 years in business informatics and computer science in two selected universities in Poland. Our study relies on a detailed review and analysis of qualitative data, obtained from a literature review and multicase-study research. In the case of the artificial intelligence domain, we have identified six areas of research, namely: general AI, machine learning (ML), natural language processing (NLP), artificial neural networks (ANNs), expert systems, and hybrids. In the case of the knowledge management domain, we have recognized eleven areas of research, regarding the following sectors: e-government, technology, space exploration, social media, manufacturing, healthcare, finance, entertainment, education, e-commerce, and business. Future research will be directed toward extending the scope by including other regions and universities as well as identifying and analyzing students' motivational factors, associated with research pro jects and higher education.

show abstract

Leveraging Context Information for Joint Entity and Relation Linking

Zhao

2019

Web and Big Data

View full text Add to dashboard Cite

DBpedia and YAGO Based System for Answering Questions in Natural Language

Cited by 3 publications

References 24 publications

Semantics-based key concepts identification for documents indexing and retrieval on the web

Semantics-based key concepts identification for documents indexing and retrieval on the web

University Students’ Research on Artificial Intelligence and Knowledge Management. A Review and Report of Multi-case Studies

Leveraging Context Information for Joint Entity and Relation Linking

Contact Info

Product

Resources

About