Markus Freitag

Beam Search Strategies for Neural Machine Translation

2017

The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-toright beam-search decoder to …

Minimum Bayes Risk Decoding with Neural Metrics of Translation Quality.

2021 · arXiv (Cornell University)

This work applies Minimum Bayes Risk (MBR) decoding to optimize diverse automated metrics of translation quality. Automatic metrics in machine translation have made tremendous progress recently. In particular, neural metrics, fine-tuned on human ratings (e.g. …

Beyond Human-Only: Evaluating Human-Machine Collaboration for Collecting High-Quality Translation Data

2024 · arXiv (Cornell University)

Collecting high-quality translations is crucial for the development and evaluation of machine translation systems. However, traditional human-only approaches are costly and slow. This study presents a comprehensive investigation of 11 approaches for acquiring translation data, …

Mitigating Metric Bias in Minimum Bayes Risk Decoding

2024 · arXiv (Cornell University)

While Minimum Bayes Risk (MBR) decoding using metrics such as COMET or MetricX has outperformed traditional decoding methods such as greedy or beam search, it introduces a challenge we refer to as metric bias. As …

MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task

2024

In this paper, we present the MetricX-24 submissions to the WMT24 Metrics Shared Task and provide details on the improvements we made over the previous version of MetricX.Our primary submission is a hybrid referencebased/-free metric, …

Fast Domain Adaptation for Neural Machine Translation

2016 · arXiv (Cornell University)

Neural Machine Translation (NMT) is a new approach for automatic translation of text from one human language into another. The basic concept in NMT is to train a large Neural Network that maximizes the translation …