Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Excerpt

This stage flags vertices with “Skip-Sentence”.  The vertex flag is the start of the sentence. This can be used to ignore a complete sentence by a later stage.

Info

Uses Sentence Filter Stage

The conditions evaluated by the processor are:

  • Sentence length, given by the token count, not vertices.
  • A list of tags that work as an exception to the count, meaning that if the tag is found within the sentence the count is irrelevant and the sentence is not flagged (whitelistingallow listing).
  • A list of tags that if found in the sentence it should be flagged (blacklistingdeny listing).

Blacklisting Deny listing a tag always has precedence over the other values, so any sentence with a blacklisted deny listed flag will always be flagged as “SKIP_SENTENCE”.  Whitelisted Allow listed tags will always have precedence over the token limit restriction. And finally token limit restriction is on effect.

Note

Sentence Filter will flag the initial vertex of the sentence with a "SKIP_SENTENCE" flag, it will not remove the sentence from the interpretation graph.

Settings and Configuration

  • Remove Short Sentences ( optional ) - Enables marking of the sentence by length limit.

  • Minimum tokens for valid sentence ( optional ) - Equal or less number of tokens in sentence.

  • Keep Sentence with Semantic Tags ( optional ) - Enables the list of tags exceptions for the length limit.

  • Keep Sentence with these tags ( optional ) - List of tags used to keep the sentence. At least one of the tags should be present on the sentence. Comma separated.

  • Mark Sentence with these tags ( optional ) - List of tags used to mark the sentence. At least one of the tags should be present on the sentence.

General Settings

Include Page
Generic Processor Config
Generic Processor Config