کنفرانس بین المللی فناوری اطلاعات و دانش

صفحه اصلی / یازدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

Using Deconvolutional Variational Autoencoder for Answer Selection in Community Question Answering

نویسندگان :

Golshan Afzali Boroujeni¹ Heshaam Faili²

1- دانشگاه تهران 2- دانشگاه تهران

کلمات کلیدی :

community question answering, answer selection, convolutional-deconvolutional, variational autoencoder

چکیده :

Answer selection in community question answering is a challenging task in natural language processing. The main problem is that there is no evaluation for the answers given by the users and one should go through all possible answers for assessing them, which is exhausting and time consuming. In this paper we propose a latent-variable model for learning the representations of the question and answer, by jointly optimizing generative and discriminative objectives. This model uses variational autoencoders (VAE) in a multi-task learning process with a classifier to produces a representation for each answer by which the classifier could classify it’s relation with correspond question with a high performance. The experimental results on two widely used datasets demonstrate that the proposed method significantly outperforms all existing models in this filed with a high margin, especially in the semi-supervised setting.