# Quality Estimation of Machine Translated Texts based on Direct Evidence from Training Data

arXiv: https://arxiv.org/abs/2306.15399 · HTML: https://mlsanity.com/paper/2306.15399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 13 references that are in the map.
- First posted on arXiv 27 Jun 2023.

## Builds on (most cited first, 3 of 3)

- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Measuring Uncertainty in Translation Quality Evaluation (TQE)](https://mlsanity.com/paper/2111.07699/) (2021)
- [PreQuEL: Quality Estimation of Machine Translation Outputs in Advance](https://mlsanity.com/paper/2205.09178/) (2022)

## Built on by (most cited first, 1 of 1)

- [Parallel Corpus Augmentation using Masked Language Models](https://mlsanity.com/paper/2410.03194/) (2024)

## Abstract (arXiv)

Current Machine Translation systems achieve very good results on a growing variety of language pairs and data sets. However, it is now well known that they produce fluent translation outputs that often can contain important meaning errors. Quality Estimation task deals with the estimation of quality of translations produced by a Machine Translation system without depending on Reference Translations. A number of approaches have been suggested over the years. In this paper we show that the parallel corpus used as training data for training the MT system holds direct clues for estimating the quality of translations produced by the MT system. Our experiments show that this simple and direct method holds promise for quality estimation of translations produced by any purely data driven machine translation system.