Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- code_search_net
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
- code
|
8 |
+
library_name: TraceBERT
|
9 |
+
---
|
10 |
+
# Model Information
|
11 |
+
|
12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
13 |
+
|
14 |
+
This model is a Java-only version of the [CodeBERT-model](https://huggingface.co/microsoft/codebert-base), trained using the [TraceBERT library](https://github.com/jinfenglin/TraceBERT).
|
15 |
+
|
16 |
+
We initialized the model with the original CodeBERT-base and then again trained only on the Java part of the dataset.
|
17 |
+
|
18 |
+
The model was used for predicting trace links between software architecture documentation and Java source code on [traceability link recovery benchmarks](https://github.com/ArDoCo/Benchmark).
|
19 |
+
|
20 |
+
### Training Data
|
21 |
+
|
22 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
23 |
+
|
24 |
+
The original CodeBERT-base model is again trained on the Java-based bi-modal data (documents & code) of [CodeSearchNet](https://huggingface.co/datasets/code_search_net).
|
25 |
+
|
26 |
+
### Usages
|
27 |
+
|
28 |
+
For TLR usage scenarios please take a look at our [replication package](https://github.com/ArDoCo/Replication-Package-ICSE24_Recovering-Trace-Links-Between-Software-Documentation-And-Code).
|
29 |
+
|
30 |
+
### Reference
|
31 |
+
1. [CodeBERT-base model](https://huggingface.co/microsoft/codebert-base)
|
32 |
+
2. [TraceBERT library](https://github.com/jinfenglin/TraceBERT)
|
33 |
+
3. [Replication Package](https://github.com/ArDoCo/Replication-Package-ICSE24_Recovering-Trace-Links-Between-Software-Documentation-And-Code)
|
34 |
+
|
35 |
+
### Citation
|
36 |
+
```bibtex
|
37 |
+
@inproceedings{keim_recovering_2024,
|
38 |
+
author = {Keim, Jan and Corallo, Sophie and Fuchß, Dominik and Hey, Tobias and Telge, Tobias and Koziolek, Anne},
|
39 |
+
year = {2024},
|
40 |
+
title = {Recovering Trace Links Between Software Documentation And Code},
|
41 |
+
eventtitle = {46th International Conference on Software Engineering},
|
42 |
+
eventtitleaddon = {ICSE 2024},
|
43 |
+
eventdate = {2024-04-14/2024-04-20},
|
44 |
+
venue = {Lissabon, Portugal},
|
45 |
+
booktitle = {Proceedings of 46th International Conference on Software Engineering (ICSE 2024)},
|
46 |
+
isbn = {979-8-4007-0217-4},
|
47 |
+
doi = {10.5445/IR/1000165692/post},
|
48 |
+
keywords = {software traceability, software architecture, documentation, transitive links, intermediate artifacts, information retrieval},
|
49 |
+
language = {english}
|
50 |
+
}
|
51 |
+
```
|