CO-STAR: Conceptualisation of Stereotypes for Analysis and Reasoning

12/01/2021
by   Teyun Kwon, et al.
0

Warning: this paper contains material which may be offensive or upsetting. While much of recent work has focused on the detection of hate speech and overtly offensive content, very little research has explored the more subtle but equally harmful language in the form of implied stereotypes. This is a challenging domain, made even more so by the fact that humans often struggle to understand and reason about stereotypes. We build on existing literature and present CO-STAR (COnceptualisation of STereotypes for Analysis and Reasoning), a novel framework which encodes the underlying concepts of implied stereotypes. We also introduce the CO-STAR training data set, which contains just over 12K structured annotations of implied stereotypes and stereotype conceptualisations, and achieve state-of-the-art results after training and manual evaluation. The CO-STAR models are, however, limited in their ability to understand more complex and subtly worded stereotypes, and our research motivates future work in developing models with more sophisticated methods for encoding common-sense knowledge.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2023

Reliable Natural Language Understanding with Large Language Models and Answer Set Programming

Humans understand language by extracting information (meaning) from sent...
research
01/10/2018

Gaussian Latent Factor Analysis under Graphical Constraints

In this paper we explored the algebraic structure of the solution space ...
research
11/28/2022

On digraphs without onion star immersions

The t-onion star is the digraph obtained from a star with 2t leaves by r...
research
08/27/2018

Empirical Analysis of Common Subgraph Isomorphism Approaches to the Lost-in-Space Star Identification Problem

The process of identifying stars is integral toward stellar based orient...
research
08/17/2021

Star transposition Gray codes for multiset permutations

Given integers k≥ 2 and a_1,…,a_k≥ 1, let a:=(a_1,…,a_k) and n:=a_1+⋯+a_...
research
07/26/2023

HBS Tilings extended: State of the art and novel observations

Penrose tilings are the most famous aperiodic tilings, and they have bee...

Please sign up or login with your details

Forgot password? Click here to reset