CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Assisting Discussion Forum Users using Deep Recurrent Neural Networks

Jacob Suorra Hagstedt P (Institutionen för data- och informationsteknik (Chalmers)) ; Olof Mogren (Institutionen för data- och informationsteknik, Datavetenskap, Algoritmer (Chalmers))
Proceedings of the 1st Workshop on Representation Learning for NLP Vol. 2016 (2016), 2016, p. 53-61.
[Konferensbidrag, refereegranskat]

We present a discussion forum assistant based on deep recurrent neural networks (RNNs). The assistant is trained to perform three different tasks when faced with a question from a user. Firstly, to recommend related posts. Secondly, to recommend other users that might be able to help. Thirdly, it recommends other channels in the forum where people may discuss related topics. Our recurrent forum assistant is evaluated experimentally by prediction accuracy for the end--to--end trainable parts, as well as by performing an end-user study. We conclude that the model generalizes well, and is helpful for the users.

Nyckelord: recurrent neural networks, rnn, virtual assistant, LSTM, deep learning, machine learning

Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2016-10-09. Senast ändrad 2016-10-09.
CPL Pubid: 243103