TY - JOUR
AU - Kim, Sunghun
AB -  Deep API Learning Xiaodong Gu§ , Hongyu Zhang , Dongmei Zhang , and Sunghun Kim§ § The Hong Kong University of Science and Technology, Hong Kong, China {xguaa,hunkim}@cse.ust.hk Microsoft Research, Beijing, China {honzhang,dongmeiz}@microsoft.com ABSTRACT Developers often wonder how to implement a certain functionality (e.g., how to parse XML files) using APIs. Obtaining an API usage sequence based on an API-related natural language query is very helpful in this regard. Given a query, existing approaches utilize information retrieval models to search for matching API sequences. These approaches treat queries and APIs as bags-of-words and lack a deep understanding of the semantics of the query. We propose DeepAPI, a deep learning based approach to generate API usage sequences for a given natural language query. Instead of a bag-of-words assumption, it learns the sequence of words in a query and the sequence of associated APIs. DeepAPI adapts a neural language model named RNN Encoder-Decoder. It encodes a word sequence (user query) into a fixed-length context vector, and generates an API sequence based on the context vector. We also augment the RNN Encoder-Decoder by considering the importance of individual APIs. We empirically evaluate our approach with more than 7 million annotated code 
TI - Deep API learning
DA - 2016-11-01
UR - https://www.deepdyve.com/lp/association-for-computing-machinery/deep-api-learning-ZHfEPx8zid
DP - DeepDyve
ER -