Singh, Mittul; Greenberg, Clayton; Klakow, Dietrich
The Custom Decay Language Model for Long Range Dependencies
Text, Speech, and Dialogue: 19th International Conference, TSD 2016, Brno , Czech Republic, September 12-16, 2016, Proceedings, Springer International Publishing, pp. 343-351, Cham, 2016, ISBN 978-3-319-45510-5.
Significant correlations between words can be observed over long distances, but contemporary language models like N-grams, Skip grams, and recurrent neural network language models (RNNLMs) require a large number of parameters to capture these dependencies, if the models can do so at all. In this paper, we propose the Custom Decay Language Model (CDLM), which captures long range correlations while maintaining sub-linear increase in parameters with vocabulary size. This model has a robust and stable training procedure (unlike RNNLMs), a more powerful modeling scheme than the Skip models, and a customizable representation. In perplexity experiments, CDLMs outperform the Skip models using fewer number of parameters. A CDLM also nominally outperformed a similar-sized RNNLM, meaning that it learned as much as the RNNLM but without recurrence.