Programming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding

Sebastian Weigelt, Vanessa Steurer, Tobias Hey, Walter F. Tichy


Abstract
The key to effortless end-user programming is natural language. We examine how to teach intelligent systems new functions, expressed in natural language. As a first step, we collected 3168 samples of teaching efforts in plain English. Then we built fuSE, a novel system that translates English function descriptions into code. Our approach is three-tiered and each task is evaluated separately. We first classify whether an intent to teach new functionality is present in the utterance (accuracy: 97.7% using BERT). Then we analyze the linguistic structure and construct a semantic model (accuracy: 97.6% using a BiLSTM). Finally, we synthesize the signature of the method, map the intermediate steps (instructions in the method body) to API calls and inject control structures (F1: 67.0% with information retrieval and knowledge-based methods). In an end-to-end evaluation on an unseen dataset fuSE synthesized 84.6% of the method signatures and 79.2% of the API calls correctly.
Anthology ID:
2020.acl-main.395
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4280–4295
Language:
URL:
https://aclanthology.org/2020.acl-main.395
DOI:
10.18653/v1/2020.acl-main.395
Bibkey:
Cite (ACL):
Sebastian Weigelt, Vanessa Steurer, Tobias Hey, and Walter F. Tichy. 2020. Programming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4280–4295, Online. Association for Computational Linguistics.
Cite (Informal):
Programming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding (Weigelt et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.395.pdf
Video:
 http://slideslive.com/38928791