no code implementations • AMTA 2022 • Geza Kovacs, John DeNero
With the internet growing increasingly multilingual, it is important to consider translating websites.
no code implementations • 24 May 2023 • Xin Liu, Daniel McDuff, Geza Kovacs, Isaac Galatzer-Levy, Jacob Sunshine, Jiening Zhan, Ming-Zher Poh, Shun Liao, Paolo Di Achille, Shwetak Patel
Large language models (LLMs) can capture rich representations of concepts that are useful for real-world tasks.
1 code implementation • NAACL 2022 • Jessy Lin, Geza Kovacs, Aditya Shastry, Joern Wuebker, John DeNero
We show that human errors in TEC exhibit a more diverse range of errors and far fewer translation fluency errors than the MT errors in automatic post-editing datasets, suggesting the need for dedicated TEC models that are specialized to correct human errors.
no code implementations • 11 Nov 2020 • Samuel Läubli, Patrick Simianer, Joern Wuebker, Geza Kovacs, Rico Sennrich, Spence Green
Widely used computer-aided translation (CAT) tools divide documents into segments such as sentences and arrange them in a side-by-side, spreadsheet-like view.