Frontiers of Information Technology & Electronic Engineering
>> 2021,
Volume 22,
Issue 7
doi:
10.1631/FITEE.2000186
Discovering semantically related technical terms and web resources in Q&A discussions
Affiliation(s): School of Computer and Network Engineering, Shanxi Datong University, Datong 037009, China; School of Software, Shanghai Jiao Tong University, Shanghai 200240, China; less
Received: 2020-04-21
Accepted: 2021-07-20
Available online: 2021-07-20
Next
Previous
Abstract
A sheer number of techniques and are available for software engineering practice and this number continues to grow. Discovering semantically similar or related and offers the opportunity to design appealing services to facilitate information retrieval and information discovery. In this study, we extract and from a community of question and answer (A) discussions and propose an approach based on a neural language model to learn the semantic representations of and in a joint low-dimensional vector space. Our approach maps and to a semantic vector space based only on the surrounding and of a technical term (or web resource) in a discussion thread, without the need for mining the text content of the discussion. We apply our approach to Stack Overflow data dump of March 2018. Through both quantitative and qualitative analyses in the clustering, search, and semantic reasoning tasks, we show that the learnt technical-term and web-resource vector representations can capture the semantic relatedness of and , and they can be exploited to support various search and semantic reasoning tasks, by means of simple -nearest neighbor search and simple algebraic operations on the learnt vector representations in the embedding space.
京公网安备 11010502051620号
