The entropy of English using PPM-based models

By W. Teahan, J. Cleary. 1996

Subfields: Natural Language Processing, Information Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Yoshua Bengio
2. Christopher D. Manning
3. Jason Aaron Edward Weston
4. Richard Socher
5. Mohit Bansal
6. Ronan Collobert
7. Yoav Goldberg
8. Jianfeng Gao

In Information Theory

1. Ronan Collobert
2. L. Eon Bottou

Citations in the corpus

• Natural Language Processing (Almost) from Scratch (2011, methodology): “Teahan and Cleary (1996) obtain entropies as low as 1.46 bits per character using variable length character n-grams.”
• Revisiting the Predictability of Language: Response Completion in Social Media (2012, background): “Some other related works on this topic include (Teahan and Cleary, 1996; Moradi et al., 1998).”
• The New C Standard (Excerpted material) An Economic and Cultural Commentary (2008, unknown): “75 bits per character[318] (a random selection from 26 letters or space would have an entropy of 4.”