no code implementations • 5 Apr 2024 • Tong Su, Xin Peng, Sarubi Thillainathan, David Guzmán, Surangika Ranathunga, En-Shiun Annie Lee
Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability and computational efficiency.
no code implementations • 18 Mar 2024 • Bo-Han Lu, Yi-Hsuan Lin, En-Shiun Annie Lee, Richard Tzong-Han Tsai
We employ a pre-trained LLaMA2-7B model specialized in Traditional Mandarin Chinese to leverage the orthographic similarities between Taiwanese Hokkien Han and Traditional Mandarin Chinese.
no code implementations • 4 Feb 2024 • Eric Khiu, Hasti Toossi, David Anugraha, Jinyu Liu, Jiaxu Li, Juan Armando Parra Flores, Leandro Acros Roman, A. Seza Doğruöz, En-Shiun Annie Lee
Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs).
1 code implementation • 2 Jun 2023 • Shravan Nayak, Surangika Ranathunga, Sarubi Thillainathan, Rikki Hung, Anthony Rinaldi, Yining Wang, Jonah Mackey, Andrew Ho, En-Shiun Annie Lee
In this paper, we show that intermediate-task fine-tuning (ITFT) of PMSS models is extremely beneficial for domain-specific NMT, especially when target domain data is limited/unavailable and the considered languages are missing or under-represented in the PMSS model.
no code implementations • Findings (ACL) 2022 • En-Shiun Annie Lee, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga, David Ifeoluwa Adelani, Ruisi Su, Arya D. McCarthy
What can pre-trained multilingual sequence-to-sequence models like mBART contribute to translating low-resource languages?
no code implementations • 29 Jun 2021 • Surangika Ranathunga, En-Shiun Annie Lee, Marjana Prifti Skenduli, Ravi Shekhar, Mehreen Alam, Rishemjit Kaur
Neural Machine Translation (NMT) has seen a tremendous spurt of growth in less than ten years, and has already entered a mature phase.
no code implementations • 10 Dec 2019 • Mehrdad Valipour, En-Shiun Annie Lee, Jaime R. Jamacaro, Carolina Bessega
To determine whether there are task-specific neurons that can be exploited for unsupervised transfer learning, we introduce a method for selecting the most important neurons to solve a specific classification task.