Summary of Qe-ebm: Using Quality Estimators As Energy Loss For Machine Translation, by Gahyun Yoo et al.
QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation
by Gahyun Yoo, Jay Yoon Lee
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach, QE-EBM, is proposed for improving machine translation by leveraging quality estimators as trainable loss networks that can directly backpropagate to the NMT model. This method outperforms strong baselines in several low and high resource target languages with English as the source language. Specifically, it achieves improvements of 2.5 BLEU, 7.1 COMET-KIWI, 5.3 COMET, and 6.4 XCOMET relative to the supervised baseline for English-to-Mongolian translation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new method called QE-EBM helps computers learn to translate languages more accurately. It uses special networks that can learn from how well they do translations. This approach beats other methods in many different language pairs, especially when there isn’t much training data available. For example, it gets better results than usual for translating English into Mongolian. |
Keywords
» Artificial intelligence » Bleu » Supervised » Translation
