- Diamantino A. Caseiro
- Pat Rondon
- Tongzhou Chen
In this paper, we present a pruning technique for maximum entropy (MaxEnt) language models. It is based on computing the exact entropy loss when removing each feature from the model, and it explicitly supports backoff features by replacing each removed feature with its backoff. The algorithm computes the loss on the training data, so it is not restricted to models with n-gram like features, allowing models with any feature, including long range skips, triggers, and contextual features such as device location.
Results on the 1-billion word corpus show large perplexity improvements relative for frequency pruned models of comparable size. Automatic speech recognition (ASR) experiments show up to 0.2\% absolute WER improvements in a large-scale cloud based mobile ASR system for Italian.