State-of-the-art generalisation research in NLP: a taxonomy and review
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
[PDF][PDF] The state of profanity obfuscation in natural language processing scientific publications
Work on hate speech has made considering rude and harmful examples in scientific
publications inevitable. This situation raises various problems, such as whether or not to …
publications inevitable. This situation raises various problems, such as whether or not to …
Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges
The growing prevalence and rapid evolution of offensive language in social media amplify
the complexities of detection, particularly highlighting the challenges in identifying such …
the complexities of detection, particularly highlighting the challenges in identifying such …
Mission: Impossible language models
Chomsky and others have very directly claimed that large language models (LLMs) are
equally capable of learning languages that are possible and impossible for humans to learn …
equally capable of learning languages that are possible and impossible for humans to learn …
Profanity in Social Media: An Analysis of Pragmatic Functions and Politeness Maxims Violation
GEA Mejia, CGA Ngo - Journal Corner of Education …, 2024 - journal.jcopublishing.com
This corpus-based study employed sociopragmatic analysis to identify the role of profrane
linguistic expressions on social media, specifically Facebook and Instagram, in terms of their …
linguistic expressions on social media, specifically Facebook and Instagram, in terms of their …
Using Deep Learning for Obscene Language Detection in Vietnamese Social Media
Nowadays, a vast volume of text data is generated by Vietnamese people daily on social
media platforms. Besides the enormous benefits, this situation creates many challenges …
media platforms. Besides the enormous benefits, this situation creates many challenges …
Hate Speech Detection Research in South Asian Languages: A Survey of Tasks, Datasets and Methods
Social media has over the years emerged as a powerful platform for communicating and
sharing views, thoughts, and opinions. However, at the same time it is being abused by …
sharing views, thoughts, and opinions. However, at the same time it is being abused by …
Tackling Sexist Hate Speech: Cross-Lingual Detection and Multilingual Insights from Social Media
A Jiang - 2024 - qmro.qmul.ac.uk
With the widespread use of social media, the proliferation of online communication presents
both opportunities and challenges for fostering a respectful and inclusive digital …
both opportunities and challenges for fostering a respectful and inclusive digital …
How Much Do Robots Understand Rudeness? Challenges in Human-Robot Interaction
This paper concerns the pressing need to understand and manage inappropriate language
within the evolving human-robot interaction (HRI) landscape. As intelligent systems and …
within the evolving human-robot interaction (HRI) landscape. As intelligent systems and …
Self-supervised learning in natural language processing
D Ruiter - 2023 - publikationen.sulb.uni-saarland.de
Most natural language processing (NLP) learning algorithms require labeled data. While this
is given for a select number of (mostly English) tasks, the availability of labeled data is …
is given for a select number of (mostly English) tasks, the availability of labeled data is …