Softregex: Generating regex from natural language descriptions using softened regex equivalence

Jun U. Park; Sang Ki Ko; Marco Cognetta; Yo Sub Han

Softregex: Generating regex from natural language descriptions using softened regex equivalence

Jun U. Park, Sang Ki Ko, Marco Cognetta, Yo Sub Han

College of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

17 Citations (Scopus)

Abstract

We continue the study of generating semantically correct regular expressions from natural language descriptions (NL). The current state-of-the-art model, SemRegex, produces regular expressions from NLs by rewarding the reinforced learning based on the semantic (rather than syntactic) equivalence between two regular expressions. Since the regular expression equivalence problem is PSPACE-complete, we introduce the EQ Reg model for computing the similarity of two regular expressions using deep neural networks. Our EQ Reg model essentially softens the equivalence of two regular expressions when used as a reward function. We then propose a new regex generation model, SoftRegex, using the EQ Reg model, and empirically demonstrate that SoftRegex substantially reduces the training time (by a factor of at least 3.6) and produces state-ofthe-art results on three benchmark datasets.

Original language	English
Title of host publication	EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics
Pages	6425-6431
Number of pages	7
ISBN (Electronic)	9781950737901
Publication status	Published - 2019
Event	2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 - Hong Kong, China Duration: 2019 Nov 3 → 2019 Nov 7

Publication series

Name	EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference

Conference

Conference	2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
Country/Territory	China
City	Hong Kong
Period	19/11/3 → 19/11/7

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

All Science Journal Classification (ASJC) codes

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Cite this

Park, J. U., Ko, S. K., Cognetta, M., & Han, Y. S. (2019). Softregex: Generating regex from natural language descriptions using softened regex equivalence. In EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference (pp. 6425-6431). (EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference). Association for Computational Linguistics.

Park, Jun U. ; Ko, Sang Ki ; Cognetta, Marco et al. / Softregex : Generating regex from natural language descriptions using softened regex equivalence. EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics, 2019. pp. 6425-6431 (EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference).

@inproceedings{343b9d6076934e05806b2dba5f44ed41,

title = "Softregex: Generating regex from natural language descriptions using softened regex equivalence",

abstract = "We continue the study of generating semantically correct regular expressions from natural language descriptions (NL). The current state-of-the-art model, SemRegex, produces regular expressions from NLs by rewarding the reinforced learning based on the semantic (rather than syntactic) equivalence between two regular expressions. Since the regular expression equivalence problem is PSPACE-complete, we introduce the EQ Reg model for computing the similarity of two regular expressions using deep neural networks. Our EQ Reg model essentially softens the equivalence of two regular expressions when used as a reward function. We then propose a new regex generation model, SoftRegex, using the EQ Reg model, and empirically demonstrate that SoftRegex substantially reduces the training time (by a factor of at least 3.6) and produces state-ofthe-art results on three benchmark datasets.",

author = "Park, {Jun U.} and Ko, {Sang Ki} and Marco Cognetta and Han, {Yo Sub}",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 ; Conference date: 03-11-2019 Through 07-11-2019",

year = "2019",

language = "English",

series = "EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference",

publisher = "Association for Computational Linguistics",

pages = "6425--6431",

booktitle = "EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference",

}

Park, JU, Ko, SK, Cognetta, M & Han, YS 2019, Softregex: Generating regex from natural language descriptions using softened regex equivalence. in EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference. EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference, Association for Computational Linguistics, pp. 6425-6431, 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, 19/11/3.

Softregex: Generating regex from natural language descriptions using softened regex equivalence. / Park, Jun U.; Ko, Sang Ki; Cognetta, Marco et al.
EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics, 2019. p. 6425-6431 (EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Softregex

T2 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019

AU - Park, Jun U.

AU - Ko, Sang Ki

AU - Cognetta, Marco

AU - Han, Yo Sub

PY - 2019

Y1 - 2019

N2 - We continue the study of generating semantically correct regular expressions from natural language descriptions (NL). The current state-of-the-art model, SemRegex, produces regular expressions from NLs by rewarding the reinforced learning based on the semantic (rather than syntactic) equivalence between two regular expressions. Since the regular expression equivalence problem is PSPACE-complete, we introduce the EQ Reg model for computing the similarity of two regular expressions using deep neural networks. Our EQ Reg model essentially softens the equivalence of two regular expressions when used as a reward function. We then propose a new regex generation model, SoftRegex, using the EQ Reg model, and empirically demonstrate that SoftRegex substantially reduces the training time (by a factor of at least 3.6) and produces state-ofthe-art results on three benchmark datasets.

AB - We continue the study of generating semantically correct regular expressions from natural language descriptions (NL). The current state-of-the-art model, SemRegex, produces regular expressions from NLs by rewarding the reinforced learning based on the semantic (rather than syntactic) equivalence between two regular expressions. Since the regular expression equivalence problem is PSPACE-complete, we introduce the EQ Reg model for computing the similarity of two regular expressions using deep neural networks. Our EQ Reg model essentially softens the equivalence of two regular expressions when used as a reward function. We then propose a new regex generation model, SoftRegex, using the EQ Reg model, and empirically demonstrate that SoftRegex substantially reduces the training time (by a factor of at least 3.6) and produces state-ofthe-art results on three benchmark datasets.

UR - http://www.scopus.com/inward/record.url?scp=85084316073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084316073&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85084316073

T3 - EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference

SP - 6425

EP - 6431

BT - EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics

Y2 - 3 November 2019 through 7 November 2019

ER -

Park JU, Ko SK, Cognetta M, Han YS. Softregex: Generating regex from natural language descriptions using softened regex equivalence. In EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics. 2019. p. 6425-6431. (EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference).

Softregex: Generating regex from natural language descriptions using softened regex equivalence

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this