← All workshopsRead The Embedding Layer

Natural Language Processing

Retrieve and combine the word vectors

BOTIE

Return the embedding row for every ID in sequence order, including duplicate IDs.
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

Return the embedding row for every ID in sequence order, including duplicate IDs.

We want related words to be able to share useful learned features. The table contains those features, and each token ID selects a row. Let's retrieve the vectors for a sequence and combine them, including repeated occurrences of the same word.

Inspect the component calculation
Look up IDs(
  Table: Embedding table
  IDs: Token IDs
)
Examples and results
Embedding table
10
02
31
Token IDs
  1. 00
  2. 11
  3. 21
Required result
10
02
02
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.

Your last tested pieces can start the full construction. An existing draft there keeps its own pieces.

A repeated token dominates the pooled representation

This check uses the pieces from “Retrieve every occurrence before averaging features”.

BOTIE

Retrieve the embedding for each token occurrence, then average by feature column. One token occurs three times and another once; the unused table row should have no influence.
Token IDs
  1. 01
  2. 11
  3. 21
  4. 30
Embedding table
40
04
88

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.

Would rearranging the same token occurrences change this mean, and what sequence information is therefore lost?

Mean pooling preserves occurrence-weighted feature averages but discards token order.

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 courseWord2vec →
← Random Indexing