Unigram-Normalized Perplexity as a Language Model Performance Measure with Different Vocabulary Sizes
This work provides a more robust evaluation metric for language model researchers, enabling fairer comparisons of models trained on different vocabulary sizes.
The paper proposes unigram-normalized Perplexity as a new metric for evaluating language model performance. This metric addresses the dependency of traditional Perplexity on vocabulary size, allowing for comparisons across models with different vocabularies.
Although Perplexity is a widely used performance metric for language models, the values are highly dependent upon the number of words in the corpus and is useful to compare performance of the same corpus only. In this paper, we propose a new metric that can be used to evaluate language model performance with different vocabulary sizes. The proposed unigram-normalized Perplexity actually presents the performance improvement of the language models from that of simple unigram model, and is robust on the vocabulary size. Both theoretical analysis and computational experiments are reported.