Reference : Assessing the Generalizability of code2vec Token Embeddings |
Scientific congresses, symposiums and conference proceedings : Paper published in a book | |||
Engineering, computing & technology : Computer science | |||
Security, Reliability and Trust | |||
http://hdl.handle.net/10993/41962 | |||
Assessing the Generalizability of code2vec Token Embeddings | |
English | |
Kang, Hong Jin [Singapore Management University > SIS] | |
Bissyande, Tegawendé François D Assise ![]() | |
David, Lo [] | |
Nov-2019 | |
Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering | |
1-12 | |
Yes | |
No | |
International | |
34th IEEE/ACM International Conference on Automated Software Engineering | |
from 10/11/2019 to 15/11/2019 | |
San Diego, California | |
United States | |
[en] Code Embeddings ; Distributed Representations ; Big Code | |
[en] Many Natural Language Processing (NLP) tasks, such as sentiment analysis or syntactic parsing, have benefited from the development of word embedding models. In particular, regardless of the training algorithms, the learned embeddings have often been shown to be generalizable to different NLP tasks. In contrast, despite recent momentum on word embeddings for source code, the literature lacks evidence of their generalizability beyond the example task they have been trained for. In this experience paper, we identify 3 potential downstream tasks, namely code comments generation, code authorship identification, and code clones detection, that source code token
embedding models can be applied to. We empirically assess a recently proposed code token embedding model, namely code2vec’s token embeddings. Code2vec was trained on the task of predicting method names, and while there is potential for using the vectors it learns on other tasks, it has not been explored in literature. Therefore, we fill this gap by focusing on its generalizability for the tasks we have identified. Eventually, we show that source code token embeddings cannot be readily leveraged for the downstream tasks. Our experiments even show that our attempts to use them do not result in any improvements over less sophisticated methods. We call for more research into effective and general use of code embeddings. | |
http://hdl.handle.net/10993/41962 |
File(s) associated to this reference | ||||||||||||||
Fulltext file(s):
| ||||||||||||||
All documents in ORBilu are protected by a user license.