You might consider Ted (Xanadu Hypertext) Nelson's "Embedded Markup Considered Harmful" as a clue as to how to win the top slot in the The Hutter Prize (rules here <http://prize.hutter1.net/hrules.htm>) or, failing that, Matt Mahoney's Large Text Compression Benchmark (rules here <http://mattmahoney.net/dc/textrules.html>):
Factor out the markup from the plain text with a mapping structure to retain the information. Then apply your advanced natural language modeling technology to compressing the plain text and compress the markup -> plain text mapping structure separately using techniques specifically for that purpose. On Wed, Dec 18, 2019 at 10:18 PM YKY (Yan King Yin, ็ๆฏ่ดค) < [email protected]> wrote: > This set of slides were written in September, just after the AGI 2019 > Conference in China, but I only got time to translate them into English > today: > > English version: > https://drive.google.com/open?id=1J9_rihrWWXvQE1-wTz5iXOXhdnHpK7Wx > > Chinese version: > https://drive.google.com/open?id=1IGfRaUc-uSSEca2D-mwF5T05JRfxUVg7 > > One contribution I'm quite proud of is that reinforcement learning can be > viewed as solving the Schrodinger equation. Though it may not be of very > high practical value ๐ > > I'm currently designing an AGI architecture borrowing ideas from Google's > BERT. I will explain this in another set of slides. > > Comments and suggestions welcome ๐ > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/Tcfe7cc93841eec23-M5e1415728f77e7318ae0daed> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tcfe7cc93841eec23-Mfdc41d604fda148d4474f097 Delivery options: https://agi.topicbox.com/groups/agi/subscription
