Bash code annotation generation method based on dual information retrieval
A technology of information retrieval and coding, applied in the computer field, can solve problems such as low efficiency and multi-time cost, and achieve high-quality results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] see figure 1 As shown, the present invention provides a kind of Bash code annotation generation method based on double information retrieval, specifically comprises the following content:
[0037] (1) Collect data from the NL2Bash corpus and the data provided by the NLC2CMD competition to obtain a high-quality corpus, and perform deduplication operations on the data in the corpus. The final corpus contains 10592 data, and the data format is .
[0038] (2) To make statistics on the data in the corpus, Table 1 and Table 2 respectively show the detailed statistics of the length of code fragments and the length of code comments in the corpus.
[0039] Table 1
[0040]
[0041] Table 2
[0042]
[0043] (3) In order to ensure a fair comparison with baseline methods, 1063 pairs of data are extracted from the corpus as the test set and the rest of the corpus as the training set according to the data partitioning method of previous studies.
[0044] (4) Enter the targe...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com