Multi-timescale Representation Learning in LSTM Language Models

Language models must capture statistical dependencies between words at timescales ranging from very short to very long. Earlier work has demonstrated that dependencies in natural language tend to decay with distance between words according to a power law. However, it is unclear how this knowledge can be used for analyzing or designing neural network language models. In this work, we derived a theory for how the memory gating mechanism in long short-term memory (LSTM) language models can capture power law decay. We found that unit timescales within an LSTM, which are determined by the forget gate bias, should follow an Inverse Gamma distribution. Experiments then showed that LSTM language models trained on natural English text learn to approximate this theoretical distribution. Further, we found that explicitly imposing the theoretical distribution upon the model during training yielded better language model perplexity overall, with particular improvements for predicting low-frequency (rare) words. Moreover, the explicit multi-timescale model selectively routes information about different types of words through units with different timescales, potentially improving model interpretability. These results demonstrate the importance of careful, theoretically-motivated analysis of memory and timescale in language models.