Natural language processing based Services Composition for Environmental management

Ordóñez, Armando; Corrales, Juan Carlos; Falcarin, Paolo

doi:10.1109/sysose.2012.6384197

Cited by 8 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, we review natural language-based approaches for dynamic service composition. If we consider an user's natural language description at one end of the problem and services at the other end, then, we find that existing literature can be broadly categorized as approaches that a) apply restrictions on how the user expresses the goal using sentence templates and/or user utterances and then use structured parsing techniques to parse the sentences against service descriptions [5], [21]; b) construct semantic graphs that represent the service description [13] [28] [27] such that those could be matched with the natural language descriptions using a lexical database such as WordNet, that groups words based on their meanings, to calculate a conceptual distance metric between concepts [23] [10]; and c) match partiallyobservable natural language description using semantic web services such as OWL-S [24] [9]. Categorical limitations of existing approaches include, (i) complex linguistic processing that employs several NLP techniques: structured parsing, extracting parts-of-speech tokens, stop-word removal, spellchecking, stemming, and text segmentation, (ii) inclusion of lexical databases such as WordNet or domain-specific ontologies that represents domain lexicons, and (iii) a weaker concept representation and similarity score for semantic matching that does not account for sentence context.…”

Section: Scalability Testmentioning

confidence: 99%

NLSC: Unrestricted Natural Language-Based Service Composition through Sentence Embeddings

Romero

Dangi

Akoju

2019

2019 IEEE International Conference on Services Computing (SCC)

View full text Add to dashboard Cite

Current approaches for service composition (assemblies of atomic services) require developers to use: (a) domain-specific semantics to formalize services that restrict the vocabulary for their descriptions, and (b) translation mechanisms for service retrieval to convert unstructured user requests to strongly-typed semantic representations. In our work, we claim that the effort to developing service descriptions, request translations, and service matching could be reduced using unrestricted natural language; allowing both: (1) end-users to intuitively express their needs using natural language, and (2) service developers to develop services without relying on syntactic/semantic description languages. Although there are some natural languagebased service composition approaches, they restrict service retrieval to syntactic/semantic matching. With recent developments in Machine learning and Natural Language Processing, we motivate the use of Sentence Embeddings by leveraging richer semantic representations of sentences for service description, matching and retrieval. Experimental results show that service composition development effort may be reduced by more than 36% while keeping a high precision/recall when matching highlevel user requests with low-level service method invocations.

show abstract

Section: Scalability Testmentioning

confidence: 99%

NLSC: Unrestricted Natural Language-Based Service Composition through Sentence Embeddings

Romero

Dangi

Akoju

2019

2019 IEEE International Conference on Services Computing (SCC)

View full text Add to dashboard Cite

show abstract

“…These approaches have good performance in specific domains [109]. The main idea is extract concepts from the user request and match them with service concepts [110].…”

Section: Comparisonmentioning

confidence: 99%

“…The authors claim that the system can extract the tasks from how-to instructions Web pages with high precision. The work of Ordoñez et al [110] present the use of natural language processing in convergent domains by translating user request and context into automated planning representations.…”

Section: Research Directionsmentioning

confidence: 99%

Towards automated composition of convergent services: A survey

Ordóñez¹,

Alcázar

Rendón

et al. 2015

Computer Communications

Self Cite

View full text Add to dashboard Cite

A convergent service is defined as a service that exploits the convergence of communication networks and at the same time takes advantage of features of the Web. Nowadays, building up a convergent service is not trivial, because although there are significant approaches that aim to automate the service composition at different levels in the Web and Telecom domains, selecting the most appropriate approach for specific case studies is complex due to the big amount of involved information and the lack of technical considerations. Thus, in this paper, we identify the relevant phases for convergent service composition and explore the existing approaches and their associated technologies for automating each phase. For each technology, the maturity and results are analysed, as well as the elements that must be considered prior to their application in real scenarios. Furthermore, we provide research directions related to the convergent service composition phases.

show abstract

“…Some technical aspects of the AUTO4L framework have been tested previously, such as the performance and the effectiveness of the natural language processing [8][9] [10]. Therefore, the emphasis was placed in performing a preliminary experimentation in the student community in order to identify a model that contains different aspects of the student profile.…”

Section: Progress In the Design Of Auto4lmentioning

confidence: 99%

“…AUTO (AUTOmated AUTO: Automated Service composition) is a framework for automatic composition of Web and Telecom services and has been applied to different domains [8], [9], [10]. Recently, AUTO is focused in teacher training for elementary public schools and Universities in Colombia this initiative has given rise to AUTO4L (AUTO for learning).…”

Section: Introductionmentioning

confidence: 99%

Including user devices and context into STEM education for minorities

Ordóñez

2014

2014 IEEE Integrated STEM Education Conference

Self Cite

View full text Add to dashboard Cite

Learning process can be enhanced by offering students, resources that are closer to their reality. Besides, the wide use of Mobile devices brings the opportunity to go beyond classrooms and computer based learning objects. The AUTO4L Framework for personalized automated composition of Web resources based the user context. AUTO4L is highly applicable to STEM classrooms. The philosophy of AUTO4L allows to students and teachers working collaboratively in order to create dynamic learning resources. AUTO4L integrates these resources with user preferences and context. AUTO4L offers a personal experience based in Mobile devices. This paper discusses the ways in which AUTO4L could be used to extend STEM beyond walls.

show abstract

Natural language processing based Services Composition for Environmental management

Cited by 8 publications

References 11 publications

NLSC: Unrestricted Natural Language-Based Service Composition through Sentence Embeddings

NLSC: Unrestricted Natural Language-Based Service Composition through Sentence Embeddings

Towards automated composition of convergent services: A survey

Including user devices and context into STEM education for minorities

Contact Info

Product

Resources

About