InfeRE: Step-by-Step Regex Generation via Chain of Inference

Automatically generating regular expressions (abbrev. regexes) from natural language description (NL2RE) has been an emerging research area. Prior studies treat regex as a linear sequence of tokens and generate the final expressions autoregressively in a single pass. They did not take into account t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE/ACM International Conference on Automated Software Engineering : [proceedings] s. 1505 - 1515
Hlavní autoři: Zhang, Shuai, Gu, Xiaodong, Chen, Yuting, Shen, Beijun
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 11.09.2023
Témata:
Benchmark testing
Chain of Inference
Codes
Decoding
Natural languages
Regex Generation
Robustness
Self-Consistency Decoding
Software engineering
Task analysis
ISSN:2643-1572
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Automatically generating regular expressions (abbrev. regexes) from natural language description (NL2RE) has been an emerging research area. Prior studies treat regex as a linear sequence of tokens and generate the final expressions autoregressively in a single pass. They did not take into account the step-by-step internal text-matching processes behind the final results. This significantly hinders the efficacy and interpretability of regex generation by neural language models. In this paper, we propose a new paradigm called InfeRE, which decomposes the generation of regexes into chains of step-bystep inference. To enhance the robustness, we introduce a self-consistency decoding mechanism that ensembles multiple outputs sampled from different models. We evaluate InfeRE on two publicly available datasets, NL-RX-Turk and KB13, and compare the results with state-of-the-art approaches and the popular tree-based generation approach TRANX. Experimental results show that InfeRE substantially outperforms previous baselines, yielding 16.3% and 14.7% improvement in DFA@5 accuracy on two datasets, respectively.
ISSN:2643-1572
DOI:10.1109/ASE56229.2023.00111