APIBot: Question answering bot for API documentation

As the carrier of Application Programming Interfaces (APIs) knowledge, API documentation plays a crucial role in how developers learn and use an API. It is also a valuable information resource for answering API-related questions, especially when developers cannot find reliable answers to their quest...

Full description

Saved in:
Bibliographic Details
Main Authors: TIAN, Yuan, THUNG, Ferdian, SHARMA, Abhishek, LO, David
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2017
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/3925
https://ink.library.smu.edu.sg/context/sis_research/article/4927/viewcontent/APIbot_ase17_afv.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-4927
record_format dspace
spelling sg-smu-ink.sis_research-49272019-06-07T06:02:16Z APIBot: Question answering bot for API documentation TIAN, Yuan THUNG, Ferdian SHARMA, Abhishek LO, David As the carrier of Application Programming Interfaces (APIs) knowledge, API documentation plays a crucial role in how developers learn and use an API. It is also a valuable information resource for answering API-related questions, especially when developers cannot find reliable answers to their questions online/offline. However, finding answers to API-related questions from API documentation might not be easy because one may have to manually go through multiple pages before reaching the relevant page, and then read and understand the information inside the relevant page to figure out the answers. To deal with this challenge, we develop APIBot, a bot that can answer API questions given API documentation as an input. APIBot is built on top of SiriusQA, the QA system from Sirius, a state of the art intelligent personal assistant. To make SiriusQA work well under software engineering scenario, we make several modifications over SiriusQA by injecting domain specific knowledge. We evaluate APIBot on 92 API questions, answers of which are known to be present in Java 8 documentation. Our experiment shows that APIBot can achieve a Hit@5 score of 0.706. 2017-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/3925 info:doi/10.1109/ASE.2017.8115628 https://ink.library.smu.edu.sg/context/sis_research/article/4927/viewcontent/APIbot_ase17_afv.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Documentation Knowledge discovery Natural languages Probabilistic logic Training Software engineering Software Software Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Documentation
Knowledge discovery
Natural languages
Probabilistic logic
Training
Software engineering
Software
Software Engineering
spellingShingle Documentation
Knowledge discovery
Natural languages
Probabilistic logic
Training
Software engineering
Software
Software Engineering
TIAN, Yuan
THUNG, Ferdian
SHARMA, Abhishek
LO, David
APIBot: Question answering bot for API documentation
description As the carrier of Application Programming Interfaces (APIs) knowledge, API documentation plays a crucial role in how developers learn and use an API. It is also a valuable information resource for answering API-related questions, especially when developers cannot find reliable answers to their questions online/offline. However, finding answers to API-related questions from API documentation might not be easy because one may have to manually go through multiple pages before reaching the relevant page, and then read and understand the information inside the relevant page to figure out the answers. To deal with this challenge, we develop APIBot, a bot that can answer API questions given API documentation as an input. APIBot is built on top of SiriusQA, the QA system from Sirius, a state of the art intelligent personal assistant. To make SiriusQA work well under software engineering scenario, we make several modifications over SiriusQA by injecting domain specific knowledge. We evaluate APIBot on 92 API questions, answers of which are known to be present in Java 8 documentation. Our experiment shows that APIBot can achieve a Hit@5 score of 0.706.
format text
author TIAN, Yuan
THUNG, Ferdian
SHARMA, Abhishek
LO, David
author_facet TIAN, Yuan
THUNG, Ferdian
SHARMA, Abhishek
LO, David
author_sort TIAN, Yuan
title APIBot: Question answering bot for API documentation
title_short APIBot: Question answering bot for API documentation
title_full APIBot: Question answering bot for API documentation
title_fullStr APIBot: Question answering bot for API documentation
title_full_unstemmed APIBot: Question answering bot for API documentation
title_sort apibot: question answering bot for api documentation
publisher Institutional Knowledge at Singapore Management University
publishDate 2017
url https://ink.library.smu.edu.sg/sis_research/3925
https://ink.library.smu.edu.sg/context/sis_research/article/4927/viewcontent/APIbot_ase17_afv.pdf
_version_ 1770573937282908160