Multitask Learning with Deep Neural Networks for Community Question Answering
This work addresses the challenge of improving answer quality in online forums for users and developers, but it is incremental as it builds on existing multitask learning methods for a specific domain.
The paper tackled the problem of community question answering by developing a deep neural network that jointly learns three related tasks to improve accuracy and convergence rates, achieving results that approach the state of the art without manual feature engineering.
In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-comment similarity. The latter is the main task, which can exploit the previous two for achieving better results. Our DNN is trained jointly on all the three cQA tasks and learns to encode questions and comments into a single vector representation shared across the multiple tasks. The results on the official challenge test set show that our approach produces higher accuracy and faster convergence rates than the individual neural networks. Additionally, our method, which does not use any manual feature engineering, approaches the state of the art established with methods that make heavy use of it.