Sentence Embedding Models for Similarity Detection of Software Requirements

Das, Souvick; Deb, Novarun; Cortesi, Agostino; Chaki, Nabendu

doi:10.1007/s42979-020-00427-1

Cited by 19 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Requirements Traceability: Requirements traceability is used to capture the relationships between the requirements, the design, and the implementation of a system [55]. We recognized 21 papers related to this task, part of which focused on detecting the relationships between requirements (inter-dependency between requirements) [56]- [66], while the remaining focused on detecting the relationships between requirements and other artifacts (design documents and source code) [55], [67]- [74]. • Requirements Clustering: Requirements clustering is used to organize software requirements into a set of clusters with high cohesion and low coupling [75].…”

Section: ) Requirements Analysismentioning

confidence: 99%

“…This part represents the second largest group of papers (24 papers) with a major increase in the last couple of years. It is noted that papers that use this kind of representations achieve promising results in many major tasks such as requirement classification [11], [50], [51], traceability [56], [58], [59], [64], ambiguity detection [106], and requirement extraction [91], [98].…”

Section: ) Advanced Embedding Representationsmentioning

confidence: 99%

See 1 more Smart Citation

The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review

2022

View full text Add to dashboard Cite

Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-toprocess representations, such as lists of features or embedding-based vector representations. These NLPbased representations are usually used at a later stage as inputs for machine learning techniques or rulebased methods. Thus, requirements representations play a major role in determining the accuracy of different approaches. In this paper, we conducted a survey in the form of a systematic literature mapping (classification) to find out (1) what are the representations used in RE tasks literature, (2) what is the main focus of these works, (3) what are the main research directions in this domain, and ( 4) what are the gaps and potential future directions. After compiling an initial pool of 2,227 papers, and applying a set of inclusion/exclusion criteria, we obtained a final pool containing 104 relevant papers. Our survey shows that the research direction has changed from the use of lexical and syntactic features to the use of advanced embedding techniques, especially in the last two years. Using advanced embedding representations has proved its effectiveness in most RE tasks (such as requirement analysis, extracting requirements from reviews and forums, and semantic-level quality tasks). However, representations that are based on lexical and syntactic features are still more appropriate for other RE tasks (such as modeling and syntax-level quality tasks) since they provide the required information for the rules and regular expressions used when handling these tasks. In addition, we identify four gaps in the existing literature, why they matter, and how future research can begin to address them.

show abstract

Section: ) Requirements Analysismentioning

confidence: 99%

Section: ) Advanced Embedding Representationsmentioning

confidence: 99%

The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review

2022

View full text Add to dashboard Cite

show abstract

“…• Requirements Traceability: Requirements traceability is used to capture the relationships between the requirements, the design, and the implementation of a system [55]. We recognized 21 papers related to this task, part of which focused on detecting the relationships between requirements (inter-dependency between requirements) [56,57,58,59,60,61,62,63,64,65,66], while the remaining focused on detecting the relationships between requirements and other artifacts (design documents and source code) [67,55,68,69,70,71,72,73,74].…”

Section: Requirements Analysismentioning

confidence: 99%

“…This part represents the second largest group of papers (24 papers) with a major increase in the last couple of years. It is noted that papers that use this kind of representations achieve promising results in many major tasks such as requirement classification [11,50,51], traceability [64,56,59,58], ambiguity detection [106], and requirement extraction [98,91].…”

Section: Advanced Embedding Representationsmentioning

confidence: 99%

The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review

Sonbol,

Rebdawi,

Ghneim

2022

Preprint

View full text Add to dashboard Cite

Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-toprocess representations, such as lists of features or embedding-based vector representations. These NLP-based representations are usually used at a later stage as inputs for machine learning techniques or rule-based methods. Thus, requirements representations play a major role in determining the accuracy of different approaches. In this paper, we conducted a survey in the form of a systematic literature mapping (classification) to find out ( 1) what are the representations used in RE tasks literature, ( 2) what is the main focus of these works, (3) what are the main research directions in this domain, and ( 4) what are the gaps and potential future directions. After compiling an initial pool of 2,227 papers, and applying a set of inclusion/exclusion criteria, we obtained a final pool containing 104 relevant papers. Our survey shows that the research direction has changed from the use of lexical and syntactic features to the use of advanced embedding techniques, especially in the last two years. Using advanced embedding representations has proved its effectiveness in most RE tasks (such as requirement analysis, extracting requirements from reviews and forums, and semantic-level quality tasks). However, representations that are based on lexical and syntactic features are still more appropriate for other RE tasks (such as modeling and syntax-level quality tasks) since they provide the required information for the rules and regular expressions used when handling these tasks. In addition, we identify four gaps in the existing literature, why they matter, and how future research can begin to address them.

show abstract

“…BERT is an open-source machine learning framework for natural language processing (NLP) designed to help computers understand language meaning in the text [16]. BERT is a Bidirectional Encoder Representations based on Transformers, using a deep learning model as shown in Figure 6 [17].…”

Section: Bidirectional Encoder Representation From Transformer (Bert) -Machine Learningmentioning

confidence: 99%

Automatic Short Answer Grading System in Indonesian Language Using BERT Machine Learning

Wijaya¹

2021

RIA

View full text Add to dashboard Cite

A system capable of automatically grading short answers is a very useful tool. The system can be created using machine learning algorithms. In this study, a machine system using BERT is proposed. BERT is an open-source system that is set to English by default. The use of languages other than English Language is a challenge to be implemented in BERT. This study proposes a novel system to implement Indonesian Language in the BERT system for automatic grading of short answers. The experimental results were measured using two measuring instruments: Cohen's Kappa coefficient and the Confusion Matrix. The result of measuring the BERT output of the implemented system has a Cohen Kappa coefficient of 0.75, a precision of 0.94, a recall of 0.96, a Specificity of 0.76 and an F1 Score of 0.95. Based on the measurement results, it can be seen that the implementation of the automatic short answer grading system in Indonesian Language using BERT machine learning has been successful.

show abstract

Sentence Embedding Models for Similarity Detection of Software Requirements

Cited by 19 publications

References 26 publications

The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review

The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review

The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review

Automatic Short Answer Grading System in Indonesian Language Using BERT Machine Learning

Contact Info

Product

Resources

About