Commit
•
aeafc38
1
Parent(s):
8ced9a6
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,9 @@ Thus, RESTBERTa might be a foundation for several Web API integration tasks.
|
|
| 15 |
Technically, RESTBERTa covers the concepts for fine-tuning a Transformer Encoder model, i.e., a pre-trained BERT model, to question answering with task-specific samples in order to prepare
|
| 16 |
a model for a specific Web API integration task.
|
| 17 |
|
|
|
|
|
|
|
|
|
|
| 18 |
# RESTBERTa for Endpoint Discovery:
|
| 19 |
This repository contains the weights of a fined-tuned CodeBERT base model for the task of endpoint discovery in Web APIs. For this, we formulate question answering as a multiple choice task:
|
| 20 |
Given a query in natural language that describes the purpose and behavior of the target endpoint, i.e., its semantics, the model should choose the endpoint from
|
|
|
|
| 15 |
Technically, RESTBERTa covers the concepts for fine-tuning a Transformer Encoder model, i.e., a pre-trained BERT model, to question answering with task-specific samples in order to prepare
|
| 16 |
a model for a specific Web API integration task.
|
| 17 |
|
| 18 |
+
The paper ["RESTBERTa: a Transformer-based question answering approach for semantic search in Web API documentation"](https://link.springer.com/article/10.1007/s10586-023-04237-x) demonstrates the application of RESTBERTa
|
| 19 |
+
to endpoint discovery, as well as semantic parameter matching:
|
| 20 |
+
|
| 21 |
# RESTBERTa for Endpoint Discovery:
|
| 22 |
This repository contains the weights of a fined-tuned CodeBERT base model for the task of endpoint discovery in Web APIs. For this, we formulate question answering as a multiple choice task:
|
| 23 |
Given a query in natural language that describes the purpose and behavior of the target endpoint, i.e., its semantics, the model should choose the endpoint from
|