A Natural Language Interface to Ontology-Based Knowledge Bases

Paredes-Valverde, Mario Andrés; Noguera-Arnaldos, José Ángel; Rodríguez-Enríquez, Cristian Aarón; Valencia‐García, Rafael; Alor-Hernández, Giner

doi:10.1007/978-3-319-19638-1_1

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most existing studies in this area have utilised a static lexicon to map the surface forms of the relevant entities to their logical forms [55], which makes scaling up such lexicons (that often consist of thousands of entities) challenging and inefficient. To tackle these challenges, KGs have been utilised for QA through development of natural language interfaces to knowledge bases (NLIKB) [45], [56]- [59]. Existing studies performing QA over KGs have focused on utilising either general or neural network-based approaches [60].…”

Section: A Question-answer Generationmentioning

confidence: 99%

Automated Question-Answering for Interactive Decision Support in Operations & Maintenance of Wind Turbines

Chatterjee

Dethlefs

2022

IEEE Access

View full text Add to dashboard Cite

Intelligent question-answering (QA) systems have witnessed increased interest in recent years, particularly in their ability to facilitate information access, data interpretation or decision support. The wind energy sector is one of the most promising sources of renewable energy, yet turbines regularly suffer from failures and operational inconsistencies, leading to downtimes and significant maintenance costs. Addressing these issues requires rapid interpretation of complex and dynamic data patterns under time-critical conditions. In this article, we present a novel approach that leverages interactive, natural language-based decision support for operations & maintenance (O&M) of wind turbines. The proposed interactive QA system allows engineers to pose domain-specific questions in natural language, and provides answers (in natural language) based on the automated retrieval of information on turbine subcomponents, their properties and interactions, from a bespoke domain-specific knowledge graph. As data for specific faults is often sparse, we propose the use of paraphrase generation as a way to augment the existing dataset. Our QA system leverages encoder-decoder models to generate Cypher queries to obtain domain-specific facts from the KG database in response to user-posed natural language questions. Experiments with an attention-based sequence-to-sequence (Seq2Seq) model and a transformer show that the transformer accurately predicts up to 89.75% of responses to input questions, outperforming the Seq2Seq model marginally by 0.76%, though being 9.46 times more computationally efficient. The proposed QA system can help support engineers and technicians during O&M to reduce turbine downtime and operational costs, thus improving the reliability of wind energy as a source of renewable energy.

show abstract

Section: A Question-answer Generationmentioning

confidence: 99%

Automated Question-Answering for Interactive Decision Support in Operations & Maintenance of Wind Turbines

Chatterjee

Dethlefs

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…1 Developed and launched by amazon.com in 2014 Natural Language Request (NLR) as an input for any discovery system has two sides. At one side, it is natural for users because the system hides the execution complexity of service requests from service users [18] while at another side, it creates challenges such as coding the natural language, inferences from codified knowledge, automatic rule digestion, and providing single solution for ambiguity resolution [19] for the system developers.…”

Section: Introductionmentioning

confidence: 99%

Addressing Natural Language Request Complexity: At Semantic Web Service Discovery Horizon

Negi¹,

Kaur²

2020

IJEAT

View full text Add to dashboard Cite

The wondrous influence of semantic web on Service-Oriented Architecture pushes it towards a realistic and self-driven architecture where publication, discovery, selection, composition, and monitoring of services are semi-automatically performed on the behalf of their hosts or mediators. In the direction of this realistic and self-driven architecture, this research work is adding one more realistic aspect of 'interpretation of natural language request' to making the service discovery more usable for novice users. Three contributions have been made: (1) description of natural language request using six-slab range (2) two algorithms for extraction, sub-request generation, inclusion of semantics and semantic matchmaking of natural language request, and (3) evaluation of proposed strategy with two semantic formalisms. The proposed algorithms handle each complex service request as an individual entity and extract the demand/s of the request by decomposing it to the simple request from conjunction, condition, and negation-oriented natural language request. The experimental evaluation of the proposed strategy signifies the given algorithms. The proposed work and result evaluation is a part of on-going research on a generic discovery mechanism for semantic web services.

show abstract

Exploration of Question-Answering Systems: Survey

Briouya,

Choukri

et al. 2023

2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM)

View full text Add to dashboard Cite

A Natural Language Interface to Ontology-Based Knowledge Bases

Cited by 3 publications

References 19 publications

Automated Question-Answering for Interactive Decision Support in Operations & Maintenance of Wind Turbines

Automated Question-Answering for Interactive Decision Support in Operations & Maintenance of Wind Turbines

Addressing Natural Language Request Complexity: At Semantic Web Service Discovery Horizon

Exploration of Question-Answering Systems: Survey

Contact Info

Product

Resources

About