Muhammad Asaduzzaman

Azmain Kabir, Shaowei Wang, Yuan Tian et al.

Technical Q&A sites are valuable for software developers seeking knowledge, but the code snippets they provide are often uncompilable and incomplete due to unresolved types and missing libraries. This poses a challenge for users who wish to reuse or analyze these snippets. Existing methods either do not focus on creating compilable code or have low success rates. To address this, we propose ZS4C, a lightweight approach for zero-shot synthesis of compilable code from incomplete snippets using Large Language Models (LLMs). ZS4C operates in two stages: first, it uses an LLM, like GPT-3.5, to identify missing import statements in a snippet; second, it collaborates with a validator (e.g., compiler) to fix compilation errors caused by incorrect imports and syntax issues. We evaluated ZS4C on the StatType-SO benchmark and a new dataset, Python-SO, which includes 539 Python snippets from Stack Overflow across the 20 most popular Python libraries. ZS4C significantly outperforms existing methods, improving the compilation rate from 63% to 95.1% compared to the state-of-the-art SnR, marking a 50.1% improvement. On average, ZS4C can infer more accurate import statements (with an F1 score of 0.98) than SnR, with an improvement of 8.5% in the F1.

Md Rashadul Hasan Rakib, Muhammad Asaduzzaman

Short text stream clustering is an important but challenging task since massive amount of text is generated from different sources such as micro-blogging, question-answering, and social news aggregation websites. One of the major challenges of clustering such massive amount of text is to cluster them within a reasonable amount of time. The existing state-of-the-art short text stream clustering methods can not cluster such massive amount of text within a reasonable amount of time as they compute similarities between a text and all the existing clusters to assign that text to a cluster. To overcome this challenge, we propose a fast short text stream clustering method (called FastStream) that efficiently index the clusters using inverted index and compute similarity between a text and a selected number of clusters while assigning a text to a cluster. In this way, we not only reduce the running time of our proposed method but also reduce the running time of several state-of-the-art short text stream clustering methods. FastStream assigns a text to a cluster (new or existing) using the dynamically computed similarity thresholds based on statistical measure. Thus our method efficiently deals with the concept drift problem. Experimental results demonstrate that FastStream outperforms the state-of-the-art short text stream clustering methods by a significant margin on several short text datasets. In addition, the running time of FastStream is several orders of magnitude faster than that of the state-of-the-art methods.