With the emergence of Web 2.0 and microservices architecture, the number of Web APIs has increased dramatically, further intensifying the demand for efficient Web API recommendation. Existing solutions typically fall into two categories: recommendation-type methods, which treat each API as a label for classification, and match-type methods, which focus on matching mashups through API retrieval. However, three critical challenges persist: 1) the semantic ambiguities in comparing API and mashup descriptions, 2) the lack of detailed comparisons between the individual API and the mashup in recommendation-type methods, and 3) time inefficiencies for API retrieval in match-type methods. To address these challenges, we propose WARBERT, a hierarchical BERT-based model for Web API recommendation. WARBERT leverages dual-component feature fusion and attention comparison to extract precise semantic representations of API and mashup descriptions. WARBERT consists of two main components: WARBERT(R) for Recommendation and WARBERT(M) for Matching. Specifically, WAR-BERT(R) serves as an initial filter, narrowing down the candidate APIs, while WARBERT(M) refines the matching process by calculating the similarity between candidate APIs and mashup. The final likelihood of a mashup being matched with an API is determined by combining the predictions from WARBERT(R) and WARBERT(M). Additionally, WARBERT(R) incorporates an auxiliary task of mashup category judgment, which enhances its effectiveness in candidate selection. Experimental results on the ProgrammableWeb dataset demonstrate that WARBERT outperforms most existing solutions and achieves improvements of up to 11.7% compared to the model MTFM (Multi-Task Fusion Model), delivering significant enhancements in accuracy and effiency.

翻译：随着Web 2.0和微服务架构的出现，Web API的数量急剧增加，进一步加剧了对高效Web API推荐的需求。现有解决方案通常分为两类：推荐型方法，将每个API视为分类标签；匹配型方法，侧重于通过API检索匹配Mashup。然而，三个关键挑战依然存在：1) 比较API与Mashup描述时的语义模糊性；2) 推荐型方法中缺乏对单个API与Mashup的详细比较；3) 匹配型方法中API检索的时间效率低下。为应对这些挑战，我们提出了WARBERT，一种基于分层BERT的Web API推荐模型。WARBERT利用双组件特征融合和注意力比较机制，提取API与Mashup描述的精确语义表示。该模型包含两个主要组件：用于推荐的WARBERT(R)和用于匹配的WARBERT(M)。具体而言，WARBERT(R)作为初始过滤器缩小候选API范围，而WARBERT(M)通过计算候选API与Mashup的相似度来优化匹配过程。Mashup与API匹配的最终可能性通过结合WARBERT(R)和WARBERT(M)的预测结果确定。此外，WARBERT(R)引入了Mashup类别判断的辅助任务，增强了其在候选选择中的有效性。在ProgrammableWeb数据集上的实验结果表明，WARBERT优于大多数现有解决方案，相比MTFM（多任务融合模型）最高提升11.7%，在准确性和效率方面实现了显著改进。