TY  - JOUR
U1  - Wissenschaftlicher Artikel
A1  - Kotstein, Sebastian
A1  - Decker, Christian
T1  - RESTBERTa: a Transformer-based question answering approach for semantic search in Web API documentation
JF  - Cluster computing : the journal of networks, software tools and applications
N2  - To enable machines to process state-of-practice Web API documentation, we propose a Transformer model for the generic task of identifying a Web API element within a syntax structure that matches a natural language query. We solve this semantic-search task with Transformer-based question answering and demonstrate the applicability of our approach to two different tasks, namely the discovery of endpoints and the identification of parameters in payload schemas. With samples from 2321 OpenAPI documentation, we prepare different datasets and fine-tune pre-trained BERT models to these two tasks. We evaluate the generalizability and the robustness of our fine-tuned models. We achieve accuracies of 81.95% for the parameter-matching and 88.44% for the endpoint-discovery task.
KW  - web API documentation
KW  - semantic search
KW  - endpoint discovery
KW  - parameter matching
KW  - question answering
KW  - BERT
Y1  - 2024
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-49175
SN  - 1386-7857
SS  - 1386-7857
U6  - https://doi.org/10.1007/s10586-023-04237-x
DO  - https://doi.org/10.1007/s10586-023-04237-x
VL  - 27
SP  - 4035
EP  - 4061
S1  - 27
PB  - Springer
CY  - Dordrecht
ER  -