Alert button
Picture for Marzena Karpinska

Marzena Karpinska

Alert button

Large language models effectively leverage document-level context for literary translation, but critical errors persist

Apr 07, 2023
Marzena Karpinska, Mohit Iyyer

Figure 1 for Large language models effectively leverage document-level context for literary translation, but critical errors persist
Figure 2 for Large language models effectively leverage document-level context for literary translation, but critical errors persist
Figure 3 for Large language models effectively leverage document-level context for literary translation, but critical errors persist
Figure 4 for Large language models effectively leverage document-level context for literary translation, but critical errors persist
Viaarxiv icon

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

Mar 23, 2023
Kalpesh Krishna, Yixiao Song, Marzena Karpinska, John Wieting, Mohit Iyyer

Figure 1 for Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Figure 2 for Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Figure 3 for Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Figure 4 for Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Viaarxiv icon

Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature

Oct 25, 2022
Katherine Thai, Marzena Karpinska, Kalpesh Krishna, Bill Ray, Moira Inghilleri, John Wieting, Mohit Iyyer

Figure 1 for Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
Figure 2 for Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
Figure 3 for Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
Figure 4 for Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
Viaarxiv icon

DEMETR: Diagnosing Evaluation Metrics for Translation

Oct 25, 2022
Marzena Karpinska, Nishant Raj, Katherine Thai, Yixiao Song, Ankita Gupta, Mohit Iyyer

Figure 1 for DEMETR: Diagnosing Evaluation Metrics for Translation
Figure 2 for DEMETR: Diagnosing Evaluation Metrics for Translation
Figure 3 for DEMETR: Diagnosing Evaluation Metrics for Translation
Figure 4 for DEMETR: Diagnosing Evaluation Metrics for Translation
Viaarxiv icon

ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution

Oct 13, 2022
Ankita Gupta, Marzena Karpinska, Wenlong Zhao, Kalpesh Krishna, Jack Merullo, Luke Yeh, Mohit Iyyer, Brendan O'Connor

Figure 1 for ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
Figure 2 for ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
Figure 3 for ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
Figure 4 for ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
Viaarxiv icon

The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation

Sep 14, 2021
Marzena Karpinska, Nader Akoury, Mohit Iyyer

Figure 1 for The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation
Figure 2 for The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation
Figure 3 for The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation
Figure 4 for The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation
Viaarxiv icon