The Context-Dependent Additive Recurrent Neural Net

Quan Hung Tran, Tuan Lai, Gholamreza Haffari, Ingrid Zukerman, Trung Bui, Hung Bui
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
Contextual sequence mapping is one of the fundamental problems in Natural Language Processing. Instead of relying solely on the information presented in a text, the learning agents have access to a strong external signal given to assist the learning process. In this paper, we propose a novel family of Recurrent Neural Network unit: the Context-dependent Additive Recurrent Neural Network (CARNN) that is designed specifically to leverage this external signal. The experimental results on public
more » ... asets in the dialog problem (Babi dialog Task 6 and Frame), contextual language model (Switchboard and Penn Discourse Tree Bank) and question answering (TrecQA) show that our novel CARNN-based architectures outperform previous methods.
doi:10.18653/v1/n18-1115 dblp:conf/naacl/TranLHZBB18 fatcat:7q2qgaecofhetdznmlaui3awd4