Your submission is now a Draft.

Once it's ready, please submit your draft for review by our team of Community Moderators. Thank you!

You have been invited to co-author this question.

When it is ready, the author will submit it for review by Community Moderators. Thanks for helping!

Pending

This question now needs to be approved by community moderators.

You have been invited to co-author this question.

It now needs to be approved by community moderators. Thanks for helping!

Hutter prize: when will a compression method achieve 1 bit-per-character on a 100MB sample of Wikipedia?

The Hutter Prize is a 50,000€ Prize for Compressing Human Knowledge. The competition's stated mission is "to encourage development of intelligent compressors/programs as a path to AGI." Since it is argued that Wikipedia is a good indication of the "Human World Knowledge," the prize often benchmarks compression progress of algorithms using the enwik8 dataset, a representative 100MB extract from Wikipedia.

Since 2006, the Hutter Prize has galvanized not only data scientists but also many AI researchers who believe that image/text compression and AI are essentially two sides of the same coin. Compression algorithms are based on the premise of finding patterns in data and are predictive in nature. Furthermore, many machine learning researchers would agree that systems with better predictive models possess more "understanding" and intelligence in general.

The bits-per-character (the number of bits required per character) for compression of enwiki8 is the de-facto measurement unit for Hutter Prize compression progression. In 2016, the state of the art was set at 1.313 bits-per-character using Suprisal-Driven Zoneout, a regularization method for RNN.

We ask:

In what year will a language model generate sequences with less than 1.0 bits-per-character on the enwik8 dataset?

Resolution occurs when a method achieves less than 1.0 bits-per-character.

Note: this question resolved before its original close time. All of your predictions came after the resolution, so you did not gain (or lose) any points for it.

Note: this question resolved before its original close time. You earned points up until the question resolution, but not afterwards.

Current points depend on your prediction, the community's prediction, and the result. Your total earned points are averaged over the lifetime of the question, so predict early to get as many points as possible! See the FAQ.