Developers often come to Stack Overflow to seek help about their programming problems. However, the technicality of the content makes the task of relevant question retrieval especially difficult. Drawing from a wide pool of natural language processing techniques, we devise a deep neural network model for question similarity that attempts to learn the semantic relationships between Stack Overflow questions using the titles and tags of posts. We additionally build around the idea of pretraining against a Quora dataset for added robustness against the noisy Stack Overflow dataset. Our contributions include an effective model for question similarity that leverages transfer learning for added robustness; a study into how the model components contribute towards model performance; and...[ Read more ]

Developers often come to Stack Overflow to seek help about their programming problems. However, the technicality of the content makes the task of relevant question retrieval especially difficult. Drawing from a wide pool of natural language processing techniques, we devise a deep neural network model for question similarity that attempts to learn the semantic relationships between Stack Overflow questions using the titles and tags of posts. We additionally build around the idea of pretraining against a Quora dataset for added robustness against the noisy Stack Overflow dataset. Our contributions include an effective model for question similarity that leverages transfer learning for added robustness; a study into how the model components contribute towards model performance; and a study into the transferability of knowledge between the Quora and Stack Overflow domains.