Complementing global and local contexts in representing API descriptions to improve API retrieval tasks
Abstract
When being trained on API documentation and tutorials, Word2vec produces vector representations to estimate the relevance between texts and API elements. However, existing Word2vec-based approaches to measure document similarities aggregate Word2vec vectors of individual words or APIs to build the representation of a document as if the words are independent. Thus, the semantics of API descriptions or code fragments are not well represented.
BibTeX
@inproceedings{Nguyen-al:FSE18,
author = {Thanh Van Nguyen and
Ngoc M. Tran and
Hung Phan and
Trong Duc Nguyen and
Linh H. Truong and
Anh Tuan Nguyen and
Hoan Anh Nguyen and
Tien N. Nguyen},
title = {Complementing global and local contexts in representing {API} descriptions to improve {API} retrieval tasks},
booktitle = {{ESEC/SIGSOFT} {FSE}},
pages = {551--562},
publisher = {{ACM}},
year = {2018},
}