Volltext-Downloads (blau) und Frontdoor-Views (grau)

RESTBERTa: a Transformer-based question answering approach for semantic search in Web API documentation

  • 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.

Download full text files

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author of HS ReutlingenKotstein, Sebastian; Decker, Christian
URN:urn:nbn:de:bsz:rt2-opus4-49175
DOI:https://doi.org/10.1007/s10586-023-04237-x
ISSN:1386-7857
eISSN:1573-7543
Erschienen in:Cluster computing : the journal of networks, software tools and applications
Publisher:Springer
Place of publication:Dordrecht
Document Type:Journal article
Language:English
Publication year:2024
Tag:BERT; endpoint discovery; parameter matching; question answering; semantic search; web API documentation
Page Number:27
DDC classes:004 Informatik
Open access?:Ja
Licence (German):License Logo  Creative Commons - CC BY - Namensnennung 4.0 International