SEQUENCE-LEVEL FEATURES: HOW GRU AND LSTM CELLS CAPTURE N-GRAMS

Xiaobing Sun, Wei Lu

Keywords: GRU, LSTM, Sequence-level, Features, N-grams

Abstract: Modern recurrent neural networks (RNN) such as Gated Recurrent Units (GRU) and Long Short-term Memory (LSTM) have demonstrated impressive results on tasks involving sequential data in practice. Despite continuous efforts on interpreting their behaviors, the exact mechanism underlying their successes in capturing sequence-level information have not been thoroughly understood. In this work, we present a study on understanding the essential features captured by GRU/LSTM cells by mathematically expanding and unrolling the hidden states. Based on the expanded and unrolled hidden states, we find there was a type of sequence-level representations brought in by the gating mechanism, which enables the cells to encode sequence-level features along with token-level features. Specifically, we show that the cells would consist of such sequence-level features similar to those of N-grams. Based on such a finding, we also found that replacing the hidden states of the standard cells with N-gram representations does not necessarily degrade performance on the sentiment analysis and language modeling tasks, indicating such features may play a significant role for GRU/LSTM cells.

One-sentence Summary: We found that the impressive performances of GRU or LSTM cells might be attributed to sequence-level representations brought in by the gating mechanism.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=20_ioE_zs_