no code implementations • 22 Feb 2024 • Spencer Rarrick, Ranjita Naik, Sundar Poudel, Vishal Chowdhary
Neural Machine Translation (NMT) continues to improve in quality and adoption, yet the inadvertent perpetuation of gender bias remains a significant concern.
no code implementations • 27 Nov 2023 • Ranjita Naik, Spencer Rarrick, Vishal Chowdhary
By using this data to fine-tune an existing NMT model, they show that gender bias can be significantly mitigated, albeit at the expense of translation quality due to catastrophic forgetting.
no code implementations • 15 Nov 2023 • Spencer Rarrick, Ranjita Naik, Sundar Poudel, Vishal Chowdhary
To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English.
1 code implementation • 7 Mar 2023 • Spencer Rarrick, Ranjita Naik, Varun Mathur, Sundar Poudel, Vishal Chowdhary
Although recent years have brought significant progress in improving translation of unambiguously gendered sentences, translation of ambiguously gendered input remains relatively unexplored.
no code implementations • WS 2019 • Akiko Eriguchi, Spencer Rarrick, Hitokazu Matsushita
In this paper, we report our submission systems (geoduck) to the Timely Disclosure task on the 6th Workshop on Asian Translation (WAT) (Nakazawa et al., 2019).