Natural Language Processing
Give the word more than an address
BOTIE
Examples, experiments and workspace controls
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.
Context for this challenge
Turn the incoming word into an ID using the vocabulary, then use that ID to retrieve its embedding row.
Botie's word ID names an entry but carries no measured semantic features. A second lookup retrieves the vector assigned to that entry in an embedding table.
Look up the incoming word's vocabulary ID, then use that ID to retrieve a row from the supplied embedding table.
Examples and results
- Word
cat
- Word-to-ID table
{ "cat": 0, "car": 1 }- Embedding rows
0.8 0.2 0.1 0.9 - Required result
0.8 0.2
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 word's ID differs from its dictionary position
This check uses the pieces from “Follow a word through its ID to its embedding row”.
BOTIE
- Word
river
- Word-to-ID table
{ "bank": 0, "river": 2, "road": 1 }- Embedding rows
0.1 0.9 0.8 0.2 0.2 0.7
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.
What would need to happen during learning for distances between these vectors to become useful?
Assigning vectors is not itself evidence of semantic structure; useful geometry depends on training and data.
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 →