Applying Natural Language Processing Techniques to Generate Open Data Web APIs Documentation

Information access globalisation has resulted in the continuous growing of online available data on the Web, especially open data portals. However, in current open data portals, data is difficult to understand and access. One of the reasons of such difficulty is the lack of suitable mechanisms to extract and learn valuable information from existing open data, such as Web Application Programming Interfaces (APIs) with proper documentation. Actually, in most cases, open data Web APIs documentation is very rudimentary, hard to follow, and sometimes incomplete or even inaccurate. To solve these data management problems, this paper proposes an approach to automatically generate Web API’s documentation which is both machine and user readable. Our approach consists of applying natural language processing techniques to create OpenAPI documentations. This manner, the access to data is facilitated because of the improvement on the comprehension of the APIs, thus promoting the reusability of data. The feasibility of our approach is presented through a case study that shows and compares the benefits of using our OpenAPI documentation process within an open data web API.

Conference: 20th International Conference on Web Engineering (ICWE)

Authors: César González Mora, Cristina Barros, Irene Garrigós, José Zubcoff, Elena Lloret and José-Norberto Mazón