Multi-cell LSTM Based Neural Language Model (1811.06477v1)

Abstract: LLMs, being at the heart of many NLP problems, are always of great interest to researchers. Neural LLMs come with the advantage of distributed representations and long range contexts. With its particular dynamics that allow the cycling of information within the network, `Recurrent neural network' (RNN) becomes an ideal paradigm for neural LLMing. Long Short-Term Memory (LSTM) architecture solves the inadequacies of the standard RNN in modeling long-range contexts. In spite of a plethora of RNN variants, possibility to add multiple memory cells in LSTM nodes was seldom explored. Here we propose a multi-cell node architecture for LSTMs and study its applicability for neural LLMing. The proposed multi-cell LSTM LLMs outperform the state-of-the-art results on well-known Penn Treebank (PTB) setup.