Write a Blog >>
MSR 2019
Sun 26 - Mon 27 May 2019 Montreal, QC, Canada
co-located with ICSE 2019

We consider the problem of developing suitable learning representations (embeddings) for library packages that capture semantic similarity among libraries. Such representations are known to improve the performance of downstream learning tasks (e.g. classification) or applications such as contextual search and analogical reasoning.

We apply word embedding techniques from natural language processing (NLP) to train embeddings for library packages (“library vectors”). Library vectors represent libraries by similar context of use as determined by import statements present in source code. Experimental results obtained from training such embeddings on three large open source software corpora reveals that library vectors capture semantically meaningful relationships among software libraries, such as the relationship between frameworks and their plug-ins and libraries commonly used together within ecosystems such as big data infrastructure projects (in Java), front-end and back-end web development frameworks (in JavaScript) and data science toolkits (in Python).

For a live demo of a contextual search engine built on import2vec, please visit https://www.code-compass.com.

Sun 26 May

msr-2019-Paper-Presentations
11:00 - 11:45: MSR 2019 Paper Presentations - Session I: Representations for Mining (Part 1) at Place du Canada
Chair(s): Chanchal K. RoyUniversity of Saskatchewan
msr-2019-papers11:00 - 11:15
Full-paper
Pre-print Media Attached
msr-2019-papers11:16 - 11:22
Short-paper
Vladimir KovalenkoTU Delft, Egor BogomolovHigher School of Economics, JetBrains Research, Timofey Bryksin, Alberto BacchelliUniversity of Zurich
DOI Pre-print Media Attached
msr-2019-papers11:23 - 11:38
Full-paper
Bart TheetenNokia Bell Labs, Belgium, Frederik Vandeputte, Tom Van CutsemNokia Bell Labs
Pre-print
msr-2019-Data-Showcase11:39 - 11:45
Talk
Vasiliki EfstathiouAthens University of Economics and Business, Diomidis SpinellisAthens University of Economics and Business
Pre-print