Recurrent Neural Networks with External Memory for Language Understanding
This addresses the gradient vanishing/exploding problem in RNNs for semantic tagging, but it is incremental as it builds on existing RNN methods.
The authors tackled the limited memory capacity of Recurrent Neural Networks (RNNs) for language understanding by adding an external memory, achieving state-of-the-art results on the ATIS dataset.
Recurrent Neural Networks (RNNs) have become increasingly popular for the task of language understanding. In this task, a semantic tagger is deployed to associate a semantic label to each word in an input sequence. The success of RNN may be attributed to its ability to memorize long-term dependence that relates the current-time semantic label prediction to the observations many time instances away. However, the memory capacity of simple RNNs is limited because of the gradient vanishing and exploding problem. We propose to use an external memory to improve memorization capability of RNNs. We conducted experiments on the ATIS dataset, and observed that the proposed model was able to achieve the state-of-the-art results. We compare our proposed model with alternative models and report analysis results that may provide insights for future research.