← All workshopsRead Learning Boundaries From Examples

Natural Language Processing

Turn boundary probabilities into pieces

BOTIE

The trained detector produces one boundary probability after each character. Apply a threshold of 0.5, then cut the original text at the resulting boundaries.
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

The trained detector produces one boundary probability after each character. Apply a threshold of 0.5, then cut the original text at the resulting boundaries.

Botie's trained boundary detector returns probabilities after characters. A cutoff must turn those scores into discrete cuts before a reader can see words.

Apply the supplied 0.5 cutoff to every after-character probability, then use the resulting indicators to cut the text.

Examples and results
Characters
南京市
Predicted boundary probabilities
  1. 00.2
  2. 10.8
  3. 21
Required result
  1. 0南京
  2. 1市
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 boundary probability is exactly at the threshold

This check uses the pieces from “Convert boundary probabilities into a segmentation”.

BOTIE

Place a boundary after a character when its predicted boundary probability is at least 0.5. Return the resulting pieces and include the equality case.
Characters
春天来了
Predicted boundary probabilities
  1. 00.1
  2. 10.5
  3. 20.1
  4. 31

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.

If a cutoff were raised, which uncertain boundaries would be more likely to disappear?

A learned detector's scores and the threshold used to act on them need separate evaluation.

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 courseN-Grams →
← Segmenting With a Hidden Model