Machine Readable Web APIs with Schema.org Action Annotations
The schema.org initiative led by the four major search engines curates a vocabulary for describing web content. The number of semantic annotations on the web are increasing, mostly due to the industrial incentives provided by those search engines. The annotations are not only consumed by search engines, but also by other automated agents like intelligent personal assistants (IPAs). However, only annotating data is not enough for automated agents to reach their full potential. Web APIs should be also annotated for automating service consumption, so the IPAs can complete tasks like booking a hotel room or buying a ticket for an event on the fly. Although there has been a vast amount of effort in the semantic web services field, the approaches did not gain too much adoption outside of academia, mainly due to lack of concrete incentives and steep learning curves. In this paper, we suggest a lightweight, bottom-up approach based on schema.org actions to annotate Web APIs. We analyse schema.org vocabulary in the scope of lightweight semantic web services literature and propose extensions where necessary. We show that schema.org actions could be a suitable vocabulary for Web API description. We demonstrate our work by annotating existing Web APIs of accommodation service providers. Additionally, we briefly demonstrate how these APIs can be used dynamically, for example, by a dialogue system.
Code (1)
Similar Papers 제목 키워드 기반
Mining Documentation to Extract Hyperparameter Schemas
AI automation tools need machine-readable hyperparameter schemas to define their search spaces. At the same time, AI libraries often come with good human-readable documentation. While such documentation contains most of …
Hierarchical Event Descriptor library schema for EEG data annotation
Standardizing terminology to annotate electrophysiological events can improve both computational research and clinical care. Sharing data enriched with standard terms can facilitate data exploration, from case studies to…
EEGUnsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel
Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.g. a dialogue state and the system actions taken at each step. These annotations can be costly to produ…
Task-Oriented Dialogue SystemsIntent Generation for Goal-Oriented Dialogue Systems based on Schema.org Annotations
Goal-oriented dialogue systems typically communicate with a backend (e.g. database, Web API) to complete certain tasks to reach a goal. The intents that a dialogue system can recognize are mostly included to the system b…
Goal-Oriented Dialogue SystemsNatural Language UnderstandingOASBuilder: Generating OpenAPI Specifications from Online API Documentation with Large Language Models
AI agents and business automation tools interacting with external web services require standardized, machine-readable information about their APIs in the form of API specifications. However, the information about APIs av…