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
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics
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
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 -