追蹤
Kelly Marchisio
Kelly Marchisio
Cohere
在 cohere.com 的電子郵件地址已通過驗證 - 首頁
標題
引用次數
引用次數
年份
When Does Unsupervised Machine Translation Work?
K Marchisio, K Duh, P Koehn
Proceedings of the 5th Conference on Machine Translation (WMT), 571-583, 2020
722020
Controlling the Reading Level of Machine Translation Output
K Marchisio, J Guo, CI Lai, P Koehn
Proceedings of Machine Translation Summit XVII: Research Track, 193-203, 2019
402019
Aya 23: Open weight releases to further multilingual progress
V Aryabumi, J Dang, D Talupuru, S Dash, D Cairuz, H Lin, B Venkitesh, ...
arXiv preprint arXiv:2405.15032, 2024
332024
Improving language plasticity via pretraining with active forgetting
Y Chen, K Marchisio, R Raileanu, D Adelani, PLE Saito Stenetorp, ...
Advances in Neural Information Processing Systems 36, 31543-31557, 2023
162023
Mini-model adaptation: Efficiently extending pretrained models to new languages via aligned shallow training
K Marchisio, P Lewis, Y Chen, M Artetxe
Findings of the Association for Computational Linguistics: ACL 2023, 2022
152022
Rlhf can speak many languages: Unlocking multilingual preference optimization for llms
J Dang, A Ahmadian, K Marchisio, J Kreutzer, A Üstün, S Hooker
arXiv preprint arXiv:2407.02552, 2024
102024
Bilingual lexicon induction for low-resource languages using graph matching via optimal transport
K Marchisio, A Saad-Eldin, K Duh, C Priebe, P Koehn
Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022
82022
Understanding and mitigating language confusion in llms
K Marchisio, WY Ko, A Bérard, T Dehaze, S Ruder
arXiv preprint arXiv:2406.20052, 2024
72024
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
K Marchisio, N Verma, K Duh, P Koehn
Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022
72022
Embedding-Enhanced GIZA++: improving low-resource word alignment using embeddings
K Marchisio, C Xiong, P Koehn
Proceedings of the 15th biennial conference of the Association for Machine …, 2022
7*2022
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces
K Marchisio, Y Park, A Saad-Eldin, A Alyakin, K Duh, C Priebe, P Koehn
Findings of the Association for Computational Linguistics: EMNLP 2021, 2021
72021
An alignment-based approach to semi-supervised bilingual lexicon induction with small parallel corpora
K Marchisio, P Koehn, C Xiong
Proceedings of Machine Translation Summit XVIII: Research Track, 293-304, 2021
72021
On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation
K Marchisio, M Freitag, D Grangier
Proceedings of the 2022 Conference of the North American Chapter of the …, 2021
42021
Johns Hopkins University Submission for WMT News Translation Task
K Marchisio, YK Lal, P Koehn
Proceedings of the Fourth Conference on Machine Translation (Volume 2 …, 2019
42019
How Does Quantization Affect Multilingual LLMs?
K Marchisio, S Dash, H Chen, D Aumiller, A Üstün, S Hooker, S Ruder
arXiv preprint arXiv:2407.03211, 2024
12024
Multilinguality from Static Embedding Spaces: Algorithmic, Geometric, and Data Considerations
KV Marchisio
Johns Hopkins University, 2023
12023
Learning a Formality-Aware Japanese Sentence Representation
HL Xinyuan, R Lee, J Chen, K Marchisio
arXiv preprint arXiv:2301.07209, 2023
2023
系統目前無法執行作業,請稍後再試。
文章 1–17