The GSI task aims at evaluating systems' ability to identify and classify stereotypes in different types of short texts. It consists of a main task, which is compulsory, and a subtask, which is not compulsory but highly recommended.
Given a short text (generally a sentence), the task consists of assigning it number (GS value) representing the degree to which it contains or refers to a stereotype.
GS values must be in the range [0,1], where 1 represent the maximum degree of stereotypicity, and have a granularity of two decimal numbers.
Given a short text (generally a sentence), the task consists of assigning it one of the stereotype categories listed below (systems are requested to assign the category to each text, independently of the degree of stereotypicity assigned).
Stereotype categories:
Role stereotypes (ROLE): They include social and cultural expectations about what women and men should do and about how they should be;
Personality stereotypes (PERS): They emotional and behavioral traits to men and women based on their gender;
Competence stereotypes (COMP): They include generalized judgements of a person's abilities based on his/her gender;
Physical stereotypes (PHYS): They refer to the expectations about the physical aspect of men and (especially) women and all aspects of personal care in general;
Sexual stereotypes (SEX): They refer to the attitude and behavior that men and women have with respect to sexuality;
Relational Stereotypes (REL): They refer to the way in which women and men should behave in interpersonal/affective relations.