4.4 Editorial Material

Naturally!: How Breakthroughs in Natural Language Processing Can Dramatically Help Developers

Related references

Note: Only part of the references are listed.
Article Computer Science, Software Engineering

Learning lenient parsing & typing via indirect supervision

Toufique Ahmed et al.

Summary: This paper presents a novel method to train a lenient parser without human-curated training data, utilizing the large corpus of correct code on GitHub and the learning capacity of Transformer-based NN architectures. With this approach, reasonable performance can be achieved in parsing and typing imperfect code, demonstrating good performance on shorter student error programs.

EMPIRICAL SOFTWARE ENGINEERING (2021)

Proceedings Paper Computer Science, Software Engineering

A Theory of Dual Channel Constraints

Casey Casalnuovo et al.

2020 IEEE/ACM 42ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: NEW IDEAS AND EMERGING RESULTS (ICSE-NIER 2020) (2020)

Proceedings Paper Computer Science, Software Engineering

Open-Vocabulary Models for Source Code

Rafael-Michael Karampatsis et al.

2020 ACM/IEEE 42ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: COMPANION PROCEEDINGS (ICSE-COMPANION 2020) (2020)

Article Psychology, Experimental

Do Programmers Prefer Predictable Expressions in Code?

Casey Casalnuovo et al.

COGNITIVE SCIENCE (2020)

Article Computer Science, Software Engineering

Studying the difference between natural and programming language corpora

Casey Casalnuovo et al.

EMPIRICAL SOFTWARE ENGINEERING (2019)

Proceedings Paper Computer Science, Artificial Intelligence

NL2Type: Inferring JavaScript Function Types from Natural Language Information

Rabee Sohail Malik et al.

2019 IEEE/ACM 41ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2019) (2019)

Article Computer Science, Software Engineering

code2vec: Learning Distributed Representations of Code

Uri Alon et al.

PROCEEDINGS OF THE ACM ON PROGRAMMING LANGUAGES-PACMPL (2019)