Dream comprehensible input engine

Here you can discuss all things Ancient Greek. Use this board to ask questions about grammar, discuss learning strategies, get help with a difficult passage of Greek, and more.
Post Reply
Textkit Member
Posts: 146
Joined: Mon Jan 28, 2019 8:21 pm

Dream comprehensible input engine

Post by Callisper » Thu Sep 19, 2019 5:11 pm

While trawling some old Textkit threads I found a gem that got me thinking:
cb wrote:
Wed May 10, 2017 1:18 am
My hope is that future students will engage with something like a comprehensible input engine (rather than a static comprehensible input text). Ancient Greek has a large data set over which unsupervised learning could crunch away and identify patterns and eventually produce content consistent with the patterns. The learning engine would then put content at you (say someone speaking to you in a virtual/augmented environment) and you'd engage, and each engagement would lead the engine to slightly optimise your learning path (like gradient descent). [...] Underlying it will be...a teaching engine that is continually being optimised for your personal engagement. What a one-on-one teacher today does basically.
I thought we might open the floor for discussion on this and the good people of Textkit could contribute their own ideas. Specifically, the question I'm interested in is as follows:

Say a 'dream engine' were developed by modern AI methods (or at some point in the future), which can produce as much Greek (or Latin etc.) as we want, and all of it entirely 'correct' and coherent (so readable, in theory, on a large-scale). That is to say, the engine can speak and write Greek 'perfectly.'

What further features would you want this engine to have, to be most useful to learners of Greek? Let's place the restriction that we haven't developed the technology for the engine to surreptitiously understand from, say, a student's responses, where intrinsically the student is weak and what they need: instead, if, for instance, you don't know a certain word, you'd have to tell the engine (e.g. select the word) - but the subsequent text could then be immediately regenerated to avoid that word except in the most comprehensible contexts (where it would be used repeatedly). Or, you might start by letting learners choose frequency levels and/or grammatical constructions, and have the text created restricted to that. As designers it's our job to include the functionalities that would be most useful or desirable to students. I'm looking for brainstorming on what that might look like, from the starting-point of an engine capable of producing correct Greek. Your ideas could have a completely different angle to mine.

I'm most eager to hear your thoughts! Particularly those of you who most strongly believe in comprehensible input as the way forward, but really anyone who thinks classical languages could be improved by practice.

User avatar
Textkit Member
Posts: 132
Joined: Wed Feb 12, 2014 1:05 am

Re: Dream comprehensible input engine

Post by mahasacham » Thu Sep 19, 2019 8:12 pm

Honestly, Id be content if Google Translate simply had the ability to accurately translate Katharevousa Greek.

Textkit Enthusiast
Posts: 444
Joined: Tue Sep 18, 2007 3:52 pm

Re: Dream comprehensible input engine

Post by cb » Thu Sep 19, 2019 10:23 pm

Hi, if we had that ideal engine, there would be two things that I would want:

1. Some way of knowing that it is producing reliable content. I’m thinking of the short film Sunspring — where AI was used to produce a film script, which is hilarious gobbledygook, and then actors played it out. If anyone hasn’t seen it, google it - it’s fantastic.

We can tell that the content is gobbledygook because it’s in our language. You would need some way of testing that in the engine — can it give you reasons for its constructions (imitated models from actual texts, grammar references, etc.)?

So the first question is figure out how we can know that we have moved beyond the Sunspring phase, and aren’t just listening to gobbledygook which technically complies with the patterns.

(Of course, in reality we are nowhere near the Sunspring phase today — I’m assuming, as you asked, that we are already at the ideal engine stage.)

2. An ability to use different subsets of the corpus of texts would be great. Today I will practice patterns drawn from Plato, tomorrow from Demosthenes.

Cheers, Chad

Textkit Enthusiast
Posts: 393
Joined: Sat Mar 30, 2013 9:10 pm

Re: Dream comprehensible input engine

Post by RandyGibbons » Mon Sep 23, 2019 7:14 pm

Callisper, your idea smells just. In its opinion, if he drinks wine by the dark sea, will Achilles compose darts? Oh may Apollo such a rhombus draw!

Post Reply