Query Expansion Based on Crowd Knowledge for Code Search

Abstract

As code search is a frequent developer activity in software development practices, improving the performance of code search is a critical task. In the text retrieval based search techniques employed in the code search, the term mismatch problem is a critical language issue for retrieval effectiveness. By reformulating the queries, query expansion provides effective ways to solve the term mismatch problem. In this paper, we propose Query Expansion based on Crowd Knowledge (QECK), a novel technique to improve the performance of code search algorithms. QECK identifies software-specific expansion words from the high quality pseudo relevance feedback question and answer pairs on Stack Overflow to automatically generate the expansion queries. Furthermore, we incorporate QECK in the classic Rocchio's model, and propose QECK based code search method QECKRocchio. We conduct three experiments to evaluate our QECK technique and investigate QECKRocchio in a large-scale corpus containing real-world code snippets and a question and answer pair collection. The results show that QECK improves the performance of three code search algorithms by up to 64 percent in Precision, and 35 percent in NDCG. Meanwhile, compared with the state-of-the-art query expansion method, the improvement of QECK Rocchio is 22 percent in Precision, and 16 percent in NDCG.Comment: 14 pages, 5 figures, IEEE Transactions on Services Computing, 201

Query expansion techniques for information retrieval: A survey

“…Some other recent applications of QE are plagiarism detection [203], event search [89,15,43], text classification [269], patent retrieval [180,181,268], dynamic process in IoT [122,123], classification of e-commerce [128], biomedical IR [1], enterprise search [174], code search [205], parallel computing in IR [179] and twitter search [151,304]. Table 7 summarizes some of the prominent and recent applications of QE in literature based on the above discussion.…”

NetNCSP: Nonoverlapping closed sequential pattern mining

“…Maximal pattern mining finds the set of patterns whose super-patterns are infrequent. Closed SPM has become a research hotspot because of its impressive compression performance [46,47] and has been widely used in many essential fields, such as recommendation systems [48], clustering analysis [49][50][51], genetic engineering [52], disease diagnosis [53], and software engineering [54,55]. However, these studies ignored the repetitions that may contain more relevant information in long sequences.…”

Bridging Semantic Gaps between Natural Languages and APIs with Word Embedding

“…Based on the human judgements, we evaluate each algorithm from two aspects, namely, given a word, how many related APIs can be correctly recommended and whether the related APIs are ranked higher than the unrelated ones. For these aspects, precision and NDCG are employed [1], [39].…”

“…Lu et al [54] reformulate a user query with synonyms generated from WordNet. Code snippets from Stack Overflow are also used for expanding queries [1], [55]. However, only a small part of Stack Overflow questions contains complete code snippets [45].…”

“…Developers usually ask technical questions on Question & Answer communities, e.g., 'How to (conduct a) sanity check (on) a date in Java'. 1 In their answers, the API 'Calen-dar#setLenient' is recommended by participants. However, • X. Li and X.…”