Dependent Bidirectional RNN with Extended-long Short-term Memory

Yuanhang Su, Yuzhong Huang, C.-C. Jay Kuo

Abstract:

In this work, we first conduct mathematical analysis on the memory, which is
defined as a function that maps an element in a sequence to the current output,
of three RNN cells; namely, the simple recurrent neural network (SRN), the long
short-term memory (LSTM) and the gated recurrent unit (GRU). Based on the
analysis, we propose a new design, called the extended-long short-term memory
(ELSTM), to extend the memory length of a cell. Next, we present a multi-task
RNN model that is robust to previous erroneous predictions, called the dependent
bidirectional recurrent neural network (DBRNN), for the sequence-in-sequenceout
(SISO) problem. Finally, the performance of the DBRNN model with the
ELSTM cell is demonstrated by experimental results.

TL;DR: A recurrent neural network cell with extended-long short-term memory and a multi-task RNN model for sequence-in-sequence-out problems

Keywords: RNN, memory, LSTM, GRU, BRNN, encoder-decoder, Natural language processing