API2CAN: a dataset & service for canonical utterance generation for REST APIs
Abstract Objectives Recently natural language interfaces (e.g., chatbots) have gained enormous attention. Such interfaces execute underlying application programming interfaces (APIs) based on the user's utterances to perform tasks (e.g., reporting weather). Supervised approaches for building su...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-09-01
|
| Series: | BMC Research Notes |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13104-021-05593-w |
| _version_ | 1818442292881522688 |
|---|---|
| author | Mohammad-Ali Yaghoub-Zadeh-Fard Boualem Benatallah |
| author_facet | Mohammad-Ali Yaghoub-Zadeh-Fard Boualem Benatallah |
| author_sort | Mohammad-Ali Yaghoub-Zadeh-Fard |
| collection | DOAJ |
| description | Abstract Objectives Recently natural language interfaces (e.g., chatbots) have gained enormous attention. Such interfaces execute underlying application programming interfaces (APIs) based on the user's utterances to perform tasks (e.g., reporting weather). Supervised approaches for building such interfaces rely upon a large set of user utterances paired with APIs. Collecting such pairs is typically starts with obtaining initial utterances for a given API method. Generating initial utterances can be considered as a machine translation task in which an API method is translated into an utterance. However, the key challenge is the lack of training samples for training domain-independent translation models. In this paper, we propose a dataset for training supervised models to generate initial utterances for APIs. Data description The dataset contains 14,370 pairs of API methods and utterances. It is built automatically by converting method descriptions of a large number of APIs to user utterances; and it is cleaned manually to ensure quality. The dataset is also accompanied with a set of microservices (e.g., translating API methods to utterances) which can facilitate the process of collecting training samples for building natural language interfaces. |
| first_indexed | 2024-12-14T18:41:50Z |
| format | Article |
| id | doaj.art-18519cab09a34f8690eb5649436f0357 |
| institution | Directory Open Access Journal |
| issn | 1756-0500 |
| language | English |
| last_indexed | 2024-12-14T18:41:50Z |
| publishDate | 2021-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Research Notes |
| spelling | doaj.art-18519cab09a34f8690eb5649436f03572022-12-21T22:51:28ZengBMCBMC Research Notes1756-05002021-09-011411310.1186/s13104-021-05593-wAPI2CAN: a dataset & service for canonical utterance generation for REST APIsMohammad-Ali Yaghoub-Zadeh-Fard0Boualem Benatallah1UNSW SydneyUNSW SydneyAbstract Objectives Recently natural language interfaces (e.g., chatbots) have gained enormous attention. Such interfaces execute underlying application programming interfaces (APIs) based on the user's utterances to perform tasks (e.g., reporting weather). Supervised approaches for building such interfaces rely upon a large set of user utterances paired with APIs. Collecting such pairs is typically starts with obtaining initial utterances for a given API method. Generating initial utterances can be considered as a machine translation task in which an API method is translated into an utterance. However, the key challenge is the lack of training samples for training domain-independent translation models. In this paper, we propose a dataset for training supervised models to generate initial utterances for APIs. Data description The dataset contains 14,370 pairs of API methods and utterances. It is built automatically by converting method descriptions of a large number of APIs to user utterances; and it is cleaned manually to ensure quality. The dataset is also accompanied with a set of microservices (e.g., translating API methods to utterances) which can facilitate the process of collecting training samples for building natural language interfaces.https://doi.org/10.1186/s13104-021-05593-wChatbotsBot developmentNatural language interfaces |
| spellingShingle | Mohammad-Ali Yaghoub-Zadeh-Fard Boualem Benatallah API2CAN: a dataset & service for canonical utterance generation for REST APIs BMC Research Notes Chatbots Bot development Natural language interfaces |
| title | API2CAN: a dataset & service for canonical utterance generation for REST APIs |
| title_full | API2CAN: a dataset & service for canonical utterance generation for REST APIs |
| title_fullStr | API2CAN: a dataset & service for canonical utterance generation for REST APIs |
| title_full_unstemmed | API2CAN: a dataset & service for canonical utterance generation for REST APIs |
| title_short | API2CAN: a dataset & service for canonical utterance generation for REST APIs |
| title_sort | api2can a dataset service for canonical utterance generation for rest apis |
| topic | Chatbots Bot development Natural language interfaces |
| url | https://doi.org/10.1186/s13104-021-05593-w |
| work_keys_str_mv | AT mohammadaliyaghoubzadehfard api2canadatasetserviceforcanonicalutterancegenerationforrestapis AT boualembenatallah api2canadatasetserviceforcanonicalutterancegenerationforrestapis |