An NLP-Based Architecture for the Autocompletion of Partial Domain Models

Burgueño, Loli; Clarisó, Robert; Gérard, Sébastien; Li, Shuai; Cabot, Jordi

doi:10.1007/978-3-030-79382-1_6

Cited by 41 publications

(21 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We envision that this lack of efficiency of our approach on these types of metamodels could be overcome in two ways. One option is to consider knowledge data (e.g., requirements, modeling environment data, ontologies) in our framework, similarly to related work [1,7]. Alternatively, we could recommend generic terms and let the modeler decide of the best combination of terms to define her specific concepts.…”

Section: Discussionmentioning

confidence: 99%

“…More recently, Burgueno et al [7] designed a NLPbased approach to assist a modeler based on textual knowledge and general knowledge data. They also enabled their assistant to take into consideration the user feedback by monitoring its interaction with the assistant.…”

Section: Related Workmentioning

confidence: 99%

“…Early approaches have focused on logic and rule-based systems with model transformation to recommend partial models [29,34,35]. More recent works have focused on the extraction of knowledge from the application domain through textual data and on the utilization of pre-trained word embedding models 1 [1,7]. On the one hand, the early approaches require to manually design rules and define rather complex approaches.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models

Weyssow,

Sahraoui,

Syriani

2021

Preprint

View full text Add to dashboard Cite

The design of conceptually sound metamodels that embody proper semantics in relation to the application domain is particularly tedious in Model-Driven Engineering. As metamodels define complex relationships between domain concepts, it is crucial for a modeler to define these concepts thoroughly while being consistent with respect to the application domain.We propose an approach to assist a modeler in the design of a metamodel by recommending relevant domain concepts in several modeling scenarios. Our approach does not require to extract knowledge from the domain or to hand-design completion rules. Instead, we design a fully data-driven approach using a deep learning model that is able to abstract domain concepts by learning from both structural and lexical metamodel properties in a corpus of thousands of independent metamodels. We evaluate our approach on a test set containing 166 metamodels, unseen during the model training, with more than 5000 test samples. Our preliminary results show that the trained model is able to provide accurate top-5 lists of relevant recommendations for concept renaming scenarios. Although promising, the results are less compelling for the scenario of the iterative construction of the metamodel, in part because of the conservative strategy we use to evaluate the recommendations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models

Weyssow,

Sahraoui,

Syriani

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Form filling can be considered as a task to auto-complete data entry for software systems, which in the literature is a popular research topic in many domains; however, most of the existing approaches propose auto-completion for different purposes or with different inputs than what we considered in this paper. In software engineering, several techniques have been proposed to provide suggestions for certain fields of software systems (e.g., priority of bug reports in bug tracking systems [71] and elements of a domain model when using domain-model designing systems [14]). Suggestions are provided by analyzing the textual data (e.g., bug reports, requirement documents) with natural language processing techniques; instead, in our work we analyze the dependencies of categorical fields.…”

Section: Related Workmentioning

confidence: 99%

A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms

Belgacem,

Li,

Bianculli

et al. 2022

Preprint

View full text Add to dashboard Cite

Users frequently interact with software systems through data entry forms. However, form filling is time-consuming and error-prone. Although several techniques have been proposed to auto-complete or pre-fill fields in the forms, they provide limited support to help users fill categorical fields, i.e., fields that require users to choose the right value among a large set of options.In this paper, we propose LAFF, a learning-based automated approach for filling categorical fields in data entry forms. LAFF first builds Bayesian Network models by learning field dependencies from a set of historical input instances, representing the values of the fields that have been filled in the past. To improve its learning ability, LAFF uses local modeling to effectively mine the local dependencies of fields in a cluster of input instances. During the form filling phase, LAFF uses such models to predict possible values of a target field, based on the values in the already-filled fields of the form and their dependencies; the predicted values (endorsed based on field dependencies and prediction confidence) are then provided to the end-user as a list of suggestions.We evaluated LAFF by assessing its effectiveness and efficiency in form filling on two datasets, one of them proprietary from the banking domain. Experimental results show that LAFF is able to provide accurate suggestions with a Mean Reciprocal Rank value above 0.73. Furthermore, LAFF is efficient, requiring at most 317 ms per suggestion.

show abstract

“…al. [6] proposed to use contextual information taken from process description to auto-generate the process. Indeed such documentation, when available, could be used to improve our autocompletion technique.…”

Section: Related Workmentioning

confidence: 99%

Augmenting Modelers with Semantic Autocompletion of Processes

Goldstein¹,

Gonzalez-Alvarez²

2021

Preprint

View full text Add to dashboard Cite

Business process modelers need to have expertise and knowledge of the domain that may not always be available to them. Therefore, they may benefit from tools that mine collections of existing processes and recommend element(s) to be added to a new process that they are constructing. In this paper, we present a method for process autocompletion at design time, that is based on the semantic similarity of subprocesses. By converting sub-processes to textual paragraphs and encoding them as numerical vectors, we can find semantically similar ones, and thereafter recommend the next element. To achieve this, we leverage a state-of-the-art technique for embedding natural language as vectors. We evaluate our approach on open source and proprietary datasets and show that our technique is accurate for processes in various domains.

show abstract

An NLP-Based Architecture for the Autocompletion of Partial Domain Models

Cited by 41 publications

References 29 publications

Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models

Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models

A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms

Augmenting Modelers with Semantic Autocompletion of Processes

Contact Info

Product

Resources

About