Developers frequently use APIs to implement certain functionality, such as parsing Excel Files, reading and writing text files line by line, etc. Developers can greatly benefit from automatic API usage sequence generation based on natural language queries for building applications in a faster and cleaner manner. Existing approaches utilize information retrieval models to search for matching API sequences given a query or use RNN based simple encoder-decoder approach to generate API sequences. As it stands, the first approach treats queries and API names as bags of words. It lacks deep comprehension of the semantics of the query. The latter approach adapts a neural language model to encode a user query into a fixed-length context vector and generate API sequences from the context vector.

Recent Pre-trained Transformer based Models (PTM) are trained on large natural language corpora in an unsupervised manner to retain contextual knowledge about the language and have found success in solving similar Natural Language Processing (NLP) problems. However, the applicability of PTMs has not yet been explored for iAPI sequence generation. Over 7 million annotations collected from GitHub are used to evaluate our approach empirically, and the dataset was also used to assess previous baselines. Based on our results, our approach generates more accurate API sequences and outperforms other related methods by 12\%.