Lossless compression of English messages using GPT-2

This lossless compressor achieves a much higher compression rate on English texts than general purpose compressors. Its typical compression ratio is 15% (number of output bits divided by the number of input bits).

The compression is achieved by using the probability of the next word computed by the GPT-2 language model released by OpenAI. It is a neural network of 1.5 billion parameters based on the Transformer architecture. It is implemented using the LibNC library and runs on a standard PC.

An arithmetic coder generates the bit stream. Each compressed character holds 15 data bits by using the CJK and the Hangul Syllables unicode ranges.

This compressor can be used to transmit text messages over very low bandwidth channels.

以上所述就是小编给大家介绍的《Lossless compression of English messages using GPT-2》，希望对大家有所帮助，如果大家有任何疑问请给我留言，小编会及时回复大家的。在此也非常感谢大家对 码农网 的支持！

查看所有标签

本站部分资源来源于网络，本站转载出于传递更多信息之目的，版权归原作者或者来源机构所有，如转载稿涉及版权问题，请联系我们。