← All workshopsRead Random Indexing

Natural Language Processing

Accumulate the context clues

BOTIE

Build the representation from the supplied context index vectors. Both observations must contribute, including any cancellation.
Ready to test
0 passed · 0 failed · 1 not run

An empty floor. Start with the information your machine needs.

Received result

Your answer will arrive here.

Examples, experiments and workspace controls
Live values

Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.

Try your own inputs

Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.

Start at an output arrow, then click or drag to an input. Drag empty space to pan. Delete removes a selection. Ctrl/Cmd+Z undoes a change.
Context for this challenge

Build the representation from the supplied context index vectors. Both observations must contribute, including any cancellation.

Botie wants to accumulate context evidence without storing a full context table. Sparse signed index vectors give each observation a contribution in a fixed-size space.

Add the two supplied index vectors coordinate by coordinate, retaining positive, negative and cancelling contributions.

Examples and results
First context vector
  1. 01
  2. 10
  3. 2-1
Second context vector
  1. 00
  2. 11
  3. 2-1
Required result
  1. 01
  2. 11
  3. 2-2
Try a fresh construction

This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.

Stuck? Inspect a worked construction

The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.

Assumptions and test precision

This is a small construction problem. The lesson explains the assumptions and the parts of the full method that this example leaves out. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.

A cancelled coordinate beside an unused coordinate

This check uses the pieces from “Accumulate both observed context vectors”.

BOTIE

Accumulate the two sparse signed context vectors. Return all five coordinates, then compare the first zero with the third zero: did they arise in the same way?
First context vector
  1. 01
  2. 10
  3. 20
  4. 3-1
  5. 40
Second context vector
  1. 0-1
  2. 11
  3. 20
  4. 30
  5. 40

Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.

Build a construction in the workspace above first. This case will test those pieces.

Could you recover both original context vectors from their sum alone?

A compact accumulated representation preserves some aggregate evidence while introducing collisions and approximation.

This is a small construction problem. The lesson explains the assumptions and the parts of the full method that this example leaves out.

Work through the Python challenges →
Continue the courseThe Embedding Layer →
← Pointwise Mutual Information