Systematic offensive stereotyping (SOS) bias in static and contextual word embeddings
Published:
venue: The Bias in AI network meeting, Durham University, the UK.
Talks
SOS: Systematic Offensive Stereotyping Bias in Word Embeddings
Published:
venue: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
On bias and fairness in large language models
Published:
venue: Internship exit talk at IBM Research, New York
Different baises in word embeddings
Published:
venue: Language models seminar at IBM Research, New York
Comparative study on word embeddings and social NLP tasks
Published:
venue: Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media
Darkness can not drive out darkness: Investigating Bias in Hate SpeechDetection Models
Published:
venue: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Does BERT Pay Attention To Cyberbullying?
Published:
venue: Data Analytics and Artificial Intelligence Research Group in Birmingham City University
A subtype of cyberbullying lies in the eye of the beholder:A comparative study on using word embeddings to detect different types of cyberbullying
Published:
venue: 73 Language at Edinburgh Lunch
Does BERT Pay Attention To Cyberbullying?
Published:
venue: 2021 International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)
Does BERT Pay Attention To Attribution?
Published:
venue: 72 Language at Edinburgh Lunch
Teargas, Water Cannons and Twitter: A case study on detecting protest repression events in Turkey 2013
Published:
venue: 2020 International Workshop on Narrative Extraction from Texts held in conjunction with the 42nd European Conference on Information Retrieval (Text2Story@ECIR 2020)