Natural Language Processing
Use a continuation piece
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
Match a starting vocabulary entry and a marked continuation, then retrieve their IDs. The ## marker belongs to the vocabulary key, not to the source spelling.
Botie can represent a word using an initial piece and a continuation entry. The continuation marker is part of the vocabulary convention, even though it does not appear in the source spelling.
Segment the word using the supplied WordPiece entries, then look up the resulting vocabulary keys.
Examples and results
- Word
playing
- WordPiece vocabulary
{ "play": 1, "##ing": 2 }- Required result
- 01
- 12
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 prefix needs two continuation pieces
This check uses the pieces from “Match a start piece and a marked continuation”.
BOTIE
- Word
unhelpful
- WordPiece vocabulary
{ "un": 2, "##help": 5, "##ful": 9 }
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.
Why would looking up ed instead of ##ed fail to follow this supplied vocabulary?
Vocabulary markers carry tokenizer-specific rules about where a piece may appear.
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 →