NLP2API: Query Reformulation for Code Search Using Crowdsourced Knowledge and Extra-Large Data Analytics

Mohammad Masudur Rahman,Chanchal Roy

doi:10.1109/icsme.2018.00086

NLP2API: Query Reformulation for Code Search Using Crowdsourced Knowledge and Extra-Large Data Analytics

Mohammad Masudur Rahman, Chanchal Roy

https://doi.org/10.1109/icsme.2018.00086

Copy DOI

Publication Date: Sep 1, 2018

Citations: 8

Affiliation: University of Saskatchewan

#Natural Language Queries #Crowdsourced Knowledge + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

Software developers frequently issue generic natural language (NL) queries for code search. Unfortunately, such queries often do not lead to any relevant results with contemporary code (or web) search engines due to vocabulary mismatch problems. In our technical research paper (accepted at ICSME 2018), we propose a technique–NLP2API–that reformulates such NL queries using crowdsourced knowledge and extra-large data analytics derived from Stack Overflow Q & A site. In this paper, we discuss all the artifacts produced by our work, and provide necessary details for downloading and verifying them.

Full Text