Extracting and Classifying Requirements from Software Engineering Contracts

Sainani, Abhishek; Anish, Preethu Rose; Joshi, Veena; Ghaisas, Smita

doi:10.1109/re48521.2020.00026

Cited by 34 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The refinement of the SQs and the indications of the three expert authors allowed the identification of the following works to ensure that main approaches to formalize specification languages for contracts were included [7,39,53,72,99], legal ontologies [6,48,54], and reviews [27,77]. Concerning the proceedings of recent conferences, the works in [2,5,40,80,82,87,89,90] have been included. The outcome of applying SQs for all six RQs and the refinement process led to the identification of a total of 447 publications.…”

Section: Search and Screening Of Selected Papersmentioning

confidence: 99%

“…Similarly to [81], the approaches proposed by [25,75] apply to very specific tasks in the annotation process. A comparison of different approaches in information extraction relying on ML is performed by Sainani et al [87] that extract requirements from large software engineering contracts. The aim is to automate the extraction and classification of such requirements to improve contract management for companies.…”

Section: Rq2: What Annotation Approaches Are Used For Semantic Annota...mentioning

confidence: 99%

“…Two main approaches have been identified; the first and most widespread refers to the implementation of NLP based rules, used in a varied range of tools to support computers in understanding and modelling NL documents [2,4,9,18,45,50,52,56,70]. The second type of approaches refer to the use of ML techniques, not necessarily specialized for NL, that apply algorithms to learn and improve from experience [25,71,75,81,87] and that frequently rely on SVM.…”

Section: Rq2: What Annotation Approaches Are Used For Semantic Annota...mentioning

confidence: 99%

“…In ontology-based semantic annotation-the most widespread approach-the process identifies instances of the concepts defined in the ontology, whereas structure annotation is commonly referred to on the definition of grammar. A legal text is parsed to perform syntactic analysis based on grammar rules to identify the structure of a phrase and how words relate to each other and mainly involves tokenization and PoS (Part of Speech) tagging [4,17,42,45,47,81,87,94]. Structural annotation is mostly performed relying on the definition of a grammar to identify structure elements of a contract and, less frequently on ML techniques [35].…”

Section: Rq2: What Annotation Approaches Are Used For Semantic Annota...mentioning

confidence: 99%

See 3 more Smart Citations

From Legal Contracts to Formal Specifications: A Systematic Literature Review

et al. 2022

View full text Add to dashboard Cite

The opportunity to automate and monitor the execution of legal contracts is gaining increasing interest in Business and Academia, thanks to the advent of smart contracts, blockchain technologies, and the Internet of Things. A critical issue in developing smart contract systems is the formalization of legal contracts, which are traditionally expressed in natural language with all the pitfalls that this entails. This paper presents a systematic literature review of papers for the main steps related to the transformation of a legal contract expressed in natural language into a formal specification. Key research studies have been identified, classified, and analyzed according to a four-step transformation process: (a) structural and semantic annotation to identify legal concepts in text, (b) identification of relationships among concepts, (c) contract domain modeling, and (d) generation of a formal specification. Each one of these steps poses serious research challenges that have been the subject of research for decades. The systematic review offers an overview of the most relevant research efforts undertaken to address each step and identifies promising approaches, best practices, and existing gaps in the literature.

show abstract

Section: Search and Screening Of Selected Papersmentioning

confidence: 99%

Section: Rq2: What Annotation Approaches Are Used For Semantic Annota...mentioning

confidence: 99%

Section: Rq2: What Annotation Approaches Are Used For Semantic Annota...mentioning

confidence: 99%

Section: Rq2: What Annotation Approaches Are Used For Semantic Annota...mentioning

confidence: 99%

See 2 more Smart Citations

From Legal Contracts to Formal Specifications: A Systematic Literature Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…• Extracting Requirements from Textual Documents: 7 papers [92,93,94,95,96,97,98] presented approaches to extract requirements from SRS documents, policies, user manuals, and emails.…”

Section: Requirements Extractionmentioning

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