Papers by Jamell Dacon

2 papers
Does Gender Matter? Towards Fairness in Dialogue Systems (2020.coling-main)

Copied to clipboard

Challenge: Recent studies have shown that AI is unfair in many real-world applications such as computer vision and recommendations.
Approach: They propose to use a benchmark dataset to study the fairness of dialogue systems to understand their bias.
Outcome: The proposed methods reduce the bias in dialogue systems significantly.
Evaluating and Mitigating Inherent Linguistic Bias of African American English through Inference (2022.coling-1)

Copied to clipboard

Challenge: Recent studies show that NLP models trained on standard English produce biased outcomes against underrepresented English varieties.
Approach: They propose a morphosyntactically-informed rule-based translation method that uses a greedy algorithm to debiase NLP models.
Outcome: The proposed framework outperforms large language models while maintaining or improving the prediction performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations