Assessing Language Models with Scaling Properties
arXiv:1804.08881
Abstract
Language models have primarily been evaluated with perplexity. While perplexity quantifies the most comprehensible prediction performance, it does not provide qualitative information on the success or failure of models. Another approach for evaluating language models is thus proposed, using the scaling properties of natural language. Five such tests are considered, with the first two accounting for the vocabulary population and the other three for the long memory of natural language. The following models were evaluated with these tests: n-grams, probabilistic context-free grammar (PCFG), Simon and Pitman-Yor (PY) processes, hierarchical PY, and neural language models. Only the neural language models exhibit the long memory properties of natural language, but to a limited degree. The effectiveness of every test of these models is also discussed.
arXiv comment14 pages, 16 figures
References in corpus (14)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- LSTM: A Search Space Odyssey
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Exploring the Limits of Language Modeling
- Pointer Sentinel Mixture Models
- Regularizing and Optimizing LSTM Language Models
- Fluctuation scaling in complex systems: Taylor's law and beyond
- Beyond word frequency: Bursts, lulls, and scaling in the temporal distributions of words
- Entropy and Long range correlations in literary English
- Entropy and Long range correlations in literary English
- On the origin of long-range correlations in texts
- Statistical laws in linguistics
- Do Neural Nets Learn Statistical Laws behind Natural Language?
- Taylor's law for Human Linguistic Sequences