TiQi: A natural language interface for querying software project data

Lin, Jinfeng; Liu, Yalin; Guo, Jin; Cleland‐Huang, Jane; Goss, William; Liu, Wenchuang; Lohar, Sugandha; Monaikul, Natawut; Rasin, Alexander

doi:10.1109/ase.2017.8115714

Cited by 10 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been only limited research where QA is applied for addressing RE problems. Existing works focus on requirements traceability [15]- [17], identifying compliance requirements [19], [71], and extracting information from online forums [72]. These techniques are mostly IR-based, with the exception of [19], which, like our approach, uses machine reading comprehension (MRC).…”

Section: Related Workmentioning

confidence: 99%

AI-based Question Answering Assistance for Analyzing Natural-language Requirements

Ezzini¹,

Abualhaija²,

Arora³

et al. 2023

Preprint

View full text Add to dashboard Cite

By virtue of being prevalently written in natural language (NL), requirements are prone to various defects, e.g., inconsistency and incompleteness. As such, requirements are frequently subject to quality assurance processes. These processes, when carried out entirely manually, are tedious and may further overlook important quality issues due to time and budget pressures. In this paper, we propose QAssist -a questionanswering (QA) approach that provides automated assistance to stakeholders, including requirements engineers, during the analysis of NL requirements. Posing a question and getting an instant answer is beneficial in various quality-assurance scenarios, e.g., incompleteness detection. Answering requirementsrelated questions automatically is challenging since the scope of the search for answers can go beyond the given requirements specification. To that end, QAssist provides support for mining external domain-knowledge resources. Our work is one of the first initiatives to bring together QA and external domain knowledge for addressing requirements engineering challenges. We evaluate QAssist on a dataset covering three application domains and containing a total of 387 question-answer pairs. We experiment with state-of-the-art QA methods, based primarily on recent large-scale language models. In our empirical study, QAssist localizes the answer to a question to three passages within the requirements specification and within the external domainknowledge resource with an average recall of 90.1% and 96.5%, respectively. QAssist extracts the actual answer to the posed question with an average accuracy of 84.2%.

show abstract

Section: Related Workmentioning

confidence: 99%

AI-based Question Answering Assistance for Analyzing Natural-language Requirements

Ezzini¹,

Abualhaija²,

Arora³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Question-answering on requirements or other artifacts, to identify requirements, has been studied to some extent in RE. Existing work mostly focuses on querying requirements documents or other textual artifacts for retrieving information related to requirements traceability [37], [38], requirements impacted by a change [39], [40], requirements-related information from online forums [41], and requirements-related information from regulatory documents [4]. Sleimi et al [4] proposed an automated querying system using semantic web technologies for taxation laws and is the closest to our approach in the RE literature.…”

Section: Related Workmentioning

confidence: 99%

Automated Question Answering for Improved Understanding of Compliance Requirements: A Multi-Document Study

Abualhaija

Arora

Sleimi

et al. 2022

2022 IEEE 30th International Requirements Engineering Conference (RE)

View full text Add to dashboard Cite

Software systems are increasingly subject to regulatory compliance. Extracting compliance requirements from regulations is challenging. Ideally, locating compliance-related information in a regulation requires a joint effort from requirements engineers and legal experts, whose availability is limited. However, regulations are typically long documents spanning hundreds of pages, containing legal jargon, applying complicated natural language structures, and including crossreferences, thus making their analysis effort-intensive. In this paper, we propose an automated questionanswering (QA) approach that assists requirements engineers in finding the legal text passages relevant to compliance requirements. Our approach utilizes largescale language models fine-tuned for QA, including BERT and three variants. We evaluate our approach on 107 question-answer pairs, manually curated by subject-matter experts, for four different European regulatory documents. Among these documents is the general data protection regulation (GDPR) -a major source for privacy-related requirements. Our empirical results show that, in ≈94% of the cases, our approach finds the text passage containing the answer to a given question among the top five passages that our approach marks as most relevant. Further, our approach successfully demarcates, in the selected passage, the right answer with an average accuracy of ≈91%.

show abstract

“…Relevant API Suggestion: There have been several studies [51,22,75,28,39,44] that return relevant functions, API classes and methods against natural language queries. McMillan et al [51] employ natural language processing (NLP), PageRank and spreading activation network (SAN) on a large corpus (e.g., FreeBSD), and identify functions relevant to a given query.…”

Section: Related Workmentioning

confidence: 99%

“…Query Reformulation for Code Search: Several earlier studies [32,39,28,76,47,44,43,55,50] reformulate a natural language query to improve the search for relevant code or software artefacts. Hill et al [32] expand a natural language query by collecting frequently co-occurring terms in the method and field signatures.…”

Section: Related Workmentioning

confidence: 99%

“…We compare with them empirically, and the detail comparison can be found in Section IV-D. There exist other studies that search source code [39,79], project repository [43], and artefact repository [44] by reformulating natural language queries. There also exist a number of query reformulation techniques [27,31,72,37,38,61,59,23,70] for concept/feature/bug/concern location.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Effective Reformulation of Query for Code Search using Crowdsourced Knowledge and Extra-Large Data Analytics

Rahman¹,

Roy²

2018

Preprint

View full text Add to dashboard Cite

Software developers frequently issue generic natural language queries for code search while using code search engines (e.g., GitHub native search, Krugle). Such queries often do not lead to any relevant results due to vocabulary mismatch problems. In this paper, we propose a novel technique that automatically identifies relevant and specific API classes from Stack Overflow Q & A site for a programming task written as a natural language query, and then reformulates the query for improved code search. We first collect candidate API classes from Stack Overflow using pseudo-relevance feedback and two term weighting algorithms, and then rank the candidates using Borda count and semantic proximity between query keywords and the API classes. The semantic proximity has been determined by an analysis of 1.3 million questions and answers of Stack Overflow. Experiments using 310 code search queries report that our technique suggests relevant API classes with 48% precision and 58% recall which are 32% and 48% higher respectively than those of the state-of-the-art. Comparisons with two stateof-the-art studies and three popular search engines (e.g., Google, Stack Overflow, and GitHub native search) report that our reformulated queries (1) outperform the queries of the stateof-the-art, and (2) significantly improve the code search results provided by these contemporary search engines.

show abstract

TiQi: A natural language interface for querying software project data

Cited by 10 publications

References 14 publications

AI-based Question Answering Assistance for Analyzing Natural-language Requirements

AI-based Question Answering Assistance for Analyzing Natural-language Requirements

Automated Question Answering for Improved Understanding of Compliance Requirements: A Multi-Document Study

Effective Reformulation of Query for Code Search using Crowdsourced Knowledge and Extra-Large Data Analytics

Contact Info

Product

Resources

About