Picture for Mara Finkelstein

Mara Finkelstein

Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms

Add code
Jun 05, 2024
Viaarxiv icon

Pinpoint, Not Criticize: Refining Large Language Models via Fine-Grained Actionable Feedback

Add code
Nov 15, 2023
Viaarxiv icon

There's no Data Like Better Data: Using QE Metrics for MT Data Filtering

Add code
Nov 09, 2023
Viaarxiv icon

Quality Control at Your Fingertips: Quality-Aware Translation Models

Add code
Oct 10, 2023
Figure 1 for Quality Control at Your Fingertips: Quality-Aware Translation Models
Figure 2 for Quality Control at Your Fingertips: Quality-Aware Translation Models
Figure 3 for Quality Control at Your Fingertips: Quality-Aware Translation Models
Figure 4 for Quality Control at Your Fingertips: Quality-Aware Translation Models
Viaarxiv icon

MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods

Add code
Sep 28, 2023
Viaarxiv icon

Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level

Add code
Aug 28, 2023
Figure 1 for Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level
Figure 2 for Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level
Figure 3 for Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level
Figure 4 for Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level
Viaarxiv icon

The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation

Add code
Aug 14, 2023
Figure 1 for The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Figure 2 for The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Figure 3 for The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Figure 4 for The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Viaarxiv icon