View source for Microsoft technology licensing, llc. (20240211224). SYNTAX UNIT TESTING AND FINE-TUNING OF NEURAL TRANSCOMPILATION MODELS simplified abstract

=SYNTAX UNIT TESTING AND FINE-TUNING OF NEURAL TRANSCOMPILATION MODELS=


==Organization Name==

[[:Category:microsoft technology licensing, llc.|microsoft technology licensing, llc.]]


[[Category:microsoft technology licensing, llc.]]

==Inventor(s)==

[[:Category:COLIN BRUCE Clement of SEATTLE WA (US)|COLIN BRUCE Clement of SEATTLE WA (US)]][[Category:COLIN BRUCE Clement of SEATTLE WA (US)]]

[[:Category:YUFAN Huang of SHANGHAI (CN)|YUFAN Huang of SHANGHAI (CN)]][[Category:YUFAN Huang of SHANGHAI (CN)]]

[[:Category:NEELAKANTAN Sundaresan of BELLEVUE WA (US)|NEELAKANTAN Sundaresan of BELLEVUE WA (US)]][[Category:NEELAKANTAN Sundaresan of BELLEVUE WA (US)]]

[[:Category:YIDING Tian of SHANGHAI (CN)|YIDING Tian of SHANGHAI (CN)]][[Category:YIDING Tian of SHANGHAI (CN)]]

[[:Category:MAOQUAN Wang of SHANGHAI (CN)|MAOQUAN Wang of SHANGHAI (CN)]][[Category:MAOQUAN Wang of SHANGHAI (CN)]]

==SYNTAX UNIT TESTING AND FINE-TUNING OF NEURAL TRANSCOMPILATION MODELS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240211224 titled 'SYNTAX UNIT TESTING AND FINE-TUNING OF NEURAL TRANSCOMPILATION MODELS

**Simplified Explanation:**
A neural transcompilation model is tested with syntax unit tests to identify syntax elements that fail to translate properly from a source programming language to a target programming language. The model is then fine-tuned with training samples to improve translation accuracy.

**Key Features and Innovation:**
- Testing syntax unit tests to identify translation defects
- Ranking syntax elements based on translation failure rates
- Fine-tuning the neural transcompilation model with training samples
- Teaching the model to learn the association between syntax elements causing translation defects and their correct translations

**Potential Applications:**
- Automated code translation between different programming languages
- Improving the accuracy and efficiency of transcompilation processes
- Enhancing the interoperability of software systems written in different languages

**Problems Solved:**
- Addressing translation defects in transcompilation processes
- Improving the accuracy of code translation between programming languages
- Enhancing the efficiency of converting code from one language to another

**Benefits:**
- Increased accuracy in translating code between programming languages
- Improved interoperability of software systems written in different languages
- Enhanced efficiency in transcompilation processes

**Commercial Applications:**
Automated Code Translation: Enhancing the accuracy and efficiency of translating code between different programming languages

**Questions about Neural Transcompilation:**
1. How does the neural transcompilation model identify syntax elements with translation defects?
2. What are the potential implications of fine-tuning the model with training samples for improving translation accuracy?


==Original Abstract Submitted==

a neural transcompilation model is tested with a set of syntax unit tests to determine the syntax elements of a source code program written in a source programming language that fail to translate properly into a target programming language. the syntax elements having a translation defect is identified and ranked according a translation failure rate. the neural transcompilation model is then fine-tuned with training samples of the syntax elements having the highest translation failure rates and their paired correct translation in order to teach the model to learn the association between the syntax elements of a source programming language causing translation defects and its correct translation in a target programming language.



[[Category:G06F8/51]]
[[Category:G06F8/41]]
[[Category:G06N3/08]]
[[Category:CPC_G06F8/51]]