text.span_overlaps

Returns a boolean tensor indicating which source and target spans overlap.

text.span_overlaps(
 source_start,
 source_limit,
 target_start,
 target_limit,
 contains=False,
 contained_by=False,
 partial_overlap=False,
 name=None
)

The source and target spans are specified using B+1 dimensional tensors, with B>=0 batch dimensions followed by a final dimension that lists the span offsets for each span in the batch:

• The ith source span in batch b1...bB starts at source_start[b1...bB, i] (inclusive), and extends to just before source_limit[b1...bB, i] (exclusive).
• The jth target span in batch b1...bB starts at target_start[b1...bB, j] (inclusive), and extends to just before target_limit[b1...bB, j] (exclusive).

result[b1...bB, i, j] is true if the ith source span overlaps with the jth target span in batch b1...bB, where a source span overlaps a target span if any of the following are true:

• The spans are identical.
• contains is true, and the source span contains the target span.
• contained_by is true, and the source span is contained by the target span.
• partial_overlap is true, and there is a non-zero overlap between the source span and the target span.

Example:

Given the following source and target spans (with no batch dimensions):

  # 0 5 10 15 20 25 30 35 40
  # |==||||||||
  # Source: [-0-] [-1-] [2] [-3-][-4-][-5-]
  # Target: [-0-][-1-] [-2-] [3] [-4-][-5-]
  # ||||||||==|
 source_start = [0, 10, 16, 20, 25, 30]
 source_limit = [5, 15, 19, 25, 30, 35]
 target_start = [0, 5, 15, 21, 27, 31]
 target_limit = [5, 10, 20, 24, 32, 37]
  
 

result[i, j] will be true at the following locations:

* `[0, 0]` (always)
* `[2, 2]` (if contained_by=True or partial_overlaps=True)
* `[3, 3]` (if contains=True or partial_overlaps=True)
* `[4, 4]` (if partial_overlaps=True)
* `[5, 4]` (if partial_overlaps=True)
* `[5, 5]` (if partial_overlaps=True)