.../data/salience/linker

The salience/linker directory contains files that aid in the mention linking of entities. Click on a filename for more detailed information below.

attributions.dat

A list of verbs that indicate the attribution of a quote to a person.

femalenames.dat

A list of common indicators of female name mentions.

malenames.dat

A list of common indicators of male name mentions.

pronouns.dat

A list of common pronouns with lexical information on their use.

quotationmarks.dat

A list of characters that are common markers of quotations.

attributions.dat

The default data/salience/linker directory contains a list of verbs in attributions.dat that are used to indicate the linking of an entity to a quotation. Users may add to or modify this list to adjust this linking functionality by creating equivalent files in a user directory.

femalenames.dat, malenames.dat

These files contain common indicators of female and male names, particularly when found in shorter mentions of a particular person's name. For example, John Smith and Mr. Smith or Jane Doe and Miss Doe.

Users can add to or modify this list to aid person name mention linking by creating an equivalent file in a user directory.

pronouns.dat

This file contains a list of pronouns and lexical information about their usage. Although users can customize this data file, it is not recommended.

quotationmarks.dat

This file contains a list of characters that indicate the beginning or ending of quotations in content. Users can add to or modify this list by creating an equivalent file in a user directory.