Mara Finkelstein
18 papers · 2023–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (33) 🌍 Conference Polyglot · Silver 🤝 Dynamic Duo (17) 🔬 Deep Specialist (15)
🗃️
Keyword Collector
(78)
⚡
Prolific Year · Productive
📈
Trend Setter
💎
Century Club · Bronze
Top co-authors
Research topics
Natural Language Processing
(16)
Applications
(15)
Machine Learning
(13)
Learning Types · Machine Learning
(8)
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(4)
Optimization & Theory
(4)
Resources & Methods
(4)
Application Areas
(3)
Core Methods
(3)
Generation
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Interdisciplinary
(1)
Keywords
machine translation
(10)
quality estimation
(7)
large language model
(4)
neural machine translation
(4)
text generation
(3)
multidimensional quality metrics
(3)
in-context learning
(2)
automatic metric
(2)
translation evaluation
(2)
machine translation evaluation
(2)
translation quality
(2)
minimum bayes risk
(2)
parallel data
(2)
minimum bayes risk decoding
(2)
evaluation metric
(2)
synthetic training data
(2)
human evaluation
(2)
multilingual model
(2)
simulated annealing
(1)
low-rank approximation
(1)
Papers
Generating Difficult-to-Translate Texts
EACL 2026
MQM Re-Annotation: A Technique for Collaborative Evaluation of Machine Translation
ACL 2026
From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set
ICML 2025
Google Translate’s Research Submission to WMT2025
EMNLP 2025
Learning from others’ mistakes: Finetuning machine translation models with span-level error annotations
ICML 2025
MetricX-25 and GemSpanEval: Google Translate Submissions to the WMT25 Evaluation Shared Task
EMNLP 2025
Pretraining Strategies using Monolingual and Parallel Data for Low-Resource Machine Translation
ACL 2025
WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects
ACL 2025
Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
NeurIPS 2024
Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data
EMNLP 2024
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
NAACL 2024
MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
ICLR 2024
MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task
EMNLP 2024
Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model
ACL 2024
MetricX-23: The Google Submission to the WMT 2023 Metrics Shared Task
EMNLP 2023
The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
EMNLP 2023
There’s No Data like Better Data: Using QE Metrics for MT Data Filtering
EMNLP 2023
Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Level
EMNLP 2023