5 papers · 1 filter
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style
Connor Baumler, Calvin Bao, Huy Nghiem +3
Despite the growing use of large language models (LLMs) for writing tasks, users may hesitate to rely on LLMs when personal style is important. Post-editing LLM-generated drafts or…
Should We be Pedantic About Reasoning Errors in Machine Translation?
Calvin Bao, Marine Carpuat
Across multiple language pairings (English \{Spanish, French, German, Mandarin, Japanese, Urdu, Cantonese\}), we find reasoning errors in translation. To quantify how often t…
Toward Machine Translation Literacy: How Lay Users Perceive and Rely on Imperfect Translations
Yimin Xiao, Yongle Zhang, Dayeon Ki +5
As Machine Translation (MT) becomes increasingly commonplace, understanding how the general public perceives and relies on imperfect MT is crucial for contextualizing MT research i…
Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work
Calvin Bao, Yow-Ting Shiue, Marine Carpuat +1
Scholars often explore literature outside of their home community of study. This exploration process is frequently hampered by field-specific jargon. Past computational work often…
Keep It Private: Unsupervised Privatization of Online Text
Calvin Bao, Marine Carpuat
Authorship obfuscation techniques hold the promise of helping people protect their privacy in online communications by automatically rewriting text to hide the identity of the orig…