Picture for Marina Fomicheva

Marina Fomicheva

Towards Explainable Evaluation Metrics for Machine Translation

Add code
Jun 22, 2023
Viaarxiv icon

Reducing Hallucinations in Neural Machine Translation with Feature Attribution

Add code
Nov 17, 2022
Viaarxiv icon

Towards Explainable Evaluation Metrics for Natural Language Generation

Add code
Mar 21, 2022
Figure 1 for Towards Explainable Evaluation Metrics for Natural Language Generation
Figure 2 for Towards Explainable Evaluation Metrics for Natural Language Generation
Figure 3 for Towards Explainable Evaluation Metrics for Natural Language Generation
Figure 4 for Towards Explainable Evaluation Metrics for Natural Language Generation
Viaarxiv icon

The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results

Add code
Oct 08, 2021
Figure 1 for The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results
Figure 2 for The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results
Figure 3 for The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results
Figure 4 for The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results
Viaarxiv icon

Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation

Add code
Sep 22, 2021
Figure 1 for Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation
Figure 2 for Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation
Figure 3 for Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation
Figure 4 for Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation
Viaarxiv icon

Translation Error Detection as Rationale Extraction

Add code
Aug 27, 2021
Figure 1 for Translation Error Detection as Rationale Extraction
Figure 2 for Translation Error Detection as Rationale Extraction
Figure 3 for Translation Error Detection as Rationale Extraction
Figure 4 for Translation Error Detection as Rationale Extraction
Viaarxiv icon

Knowledge Distillation for Quality Estimation

Add code
Jul 01, 2021
Figure 1 for Knowledge Distillation for Quality Estimation
Figure 2 for Knowledge Distillation for Quality Estimation
Figure 3 for Knowledge Distillation for Quality Estimation
Figure 4 for Knowledge Distillation for Quality Estimation
Viaarxiv icon

Backtranslation Feedback Improves User Confidence in MT, Not Quality

Add code
Apr 12, 2021
Figure 1 for Backtranslation Feedback Improves User Confidence in MT, Not Quality
Figure 2 for Backtranslation Feedback Improves User Confidence in MT, Not Quality
Figure 3 for Backtranslation Feedback Improves User Confidence in MT, Not Quality
Figure 4 for Backtranslation Feedback Improves User Confidence in MT, Not Quality
Viaarxiv icon

Exploring Supervised and Unsupervised Rewards in Machine Translation

Add code
Feb 22, 2021
Figure 1 for Exploring Supervised and Unsupervised Rewards in Machine Translation
Figure 2 for Exploring Supervised and Unsupervised Rewards in Machine Translation
Figure 3 for Exploring Supervised and Unsupervised Rewards in Machine Translation
Figure 4 for Exploring Supervised and Unsupervised Rewards in Machine Translation
Viaarxiv icon

MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset

Add code
Oct 09, 2020
Figure 1 for MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset
Figure 2 for MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset
Figure 3 for MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset
Figure 4 for MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset
Viaarxiv icon