Skip to content

span_overlaps.md

Latest commit

 

History

History
183 lines (159 loc) · 4.93 KB

span_overlaps.md

File metadata and controls

183 lines (159 loc) · 4.93 KB

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

text.span_overlaps

View source

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)

Args

`source_start` A B+1 dimensional potentially ragged tensor with shape `[D1...DB, source_size]`: the start offset of each source span.
`source_limit` A B+1 dimensional potentially ragged tensor with shape `[D1...DB, source_size]`: the limit offset of each source span.
`target_start` A B+1 dimensional potentially ragged tensor with shape `[D1...DB, target_size]`: the start offset of each target span.
`target_limit` A B+1 dimensional potentially ragged tensor with shape `[D1...DB, target_size]`: the limit offset of each target span.
`contains` If true, then a source span is considered to overlap a target span when the source span contains the target span.
`contained_by` If true, then a source span is considered to overlap a target span when the source span is contained by the target span.
`partial_overlap` If true, then a source span is considered to overlap a target span when the source span partially overlaps the target span.
`name` A name for the operation (optional).

Returns

A B+2 dimensional potentially ragged boolean tensor with shape `[D1...DB, source_size, target_size]`.

Raises

`ValueError` If the span tensors are incompatible.