Can QE-informed (Re)Translation lead to Error Correction?

• URL: http://arxiv.org/abs/2511.13884v1
• Date: Mon, 17 Nov 2025 20:10:47 GMT
• Title: Can QE-informed (Re)Translation lead to Error Correction?
• Abstract summary: The paper presents two approaches submitted to the WMT 2025 Automated Translation Quality Evaluation Systems Task 3.<n>We investigate a training-free approach - QE-informed Retranslation, and compare it with another within the same training-free paradigm.<n>The two proposed approaches achieved a Delta COMET score of 0.0201 and -0.0108, respectively, leading the first approach to achieve the winning position on the subtask leaderboard.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The paper presents two approaches submitted to the WMT 2025 Automated Translation Quality Evaluation Systems Task 3 - Quality Estimation (QE)-informed Segment-level Error Correction. While jointly training QE systems with Automatic Post-Editing (APE) has shown improved performance for both tasks, APE systems are still known to overcorrect the output of Machine Translation (MT), leading to a degradation in performance. We investigate a simple training-free approach - QE-informed Retranslation, and compare it with another within the same training-free paradigm. Our winning approach selects the highest-quality translation from multiple candidates generated by different LLMs. The second approach, more akin to APE, instructs an LLM to replace error substrings as specified in the provided QE explanation(s). A conditional heuristic was employed to minimise the number of edits, with the aim of maximising the Gain-to-Edit ratio. The two proposed approaches achieved a Delta COMET score of 0.0201 and -0.0108, respectively, leading the first approach to achieve the winning position on the subtask leaderboard.

Related papers

• Beyond Scalar Scores: Reinforcement Learning for Error-Aware Quality Estimation of Machine Translation [10.050982803590903]
  Quality Estimation aims to assess the quality of machine translation (MT) outputs without relying on reference translations.<n>We introduce the first segment-level QE dataset for English to Malayalam, a severely resource-scarce language pair.<n>We introduce ALOPE-RL, a policy-based reinforcement learning framework that trains efficient adapters.
  arXiv  Detail & Related papers  (2026-02-09T12:42:41Z)
• Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing [43.354917413940534]
  We propose a technique to mitigate over-correction by incorporating word-level Quality Estimation information during the decoding process.<n>Our experiments on English-German, English-Hindi, and English-Marathi language pairs show the proposed approach yields significant improvements.
  arXiv  Detail & Related papers  (2025-01-28T19:46:18Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators [53.91199933655421]
  Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment.<n>We introduce a universal and training-free framework, $textbfMQM-APE, based on the idea of filtering out non-impactful errors.<n>Experiments show that our approach consistently improves both the reliability and quality of error spans against GEMBA-MQM.
  arXiv  Detail & Related papers  (2024-09-22T06:43:40Z)
• TasTe: Teaching Large Language Models to Translate through Self-Reflection [82.83958470745381]
  Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. We propose the TasTe framework, which stands for translating through self-reflection. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T17:21:21Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model [75.66013048128302]
  In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training. We first identify the overoptimization problem during QE-based feedback training, manifested as an increase in reward while translation quality declines. To address the problem, we adopt a simple yet effective method that uses rules to detect the incorrect translations and assigns a penalty term to the reward scores of them.
  arXiv  Detail & Related papers  (2024-01-23T16:07:43Z)
• APE-then-QE: Correcting then Filtering Pseudo Parallel Corpora for MT Training Data Creation [48.47548479232714]
  We propose a repair-filter-use methodology that uses an APE system to correct errors on the target side of the Machine Translation training data. We select the sentence pairs from the original and corrected sentence pairs based on the quality scores computed using a Quality Estimation (QE) model. We observe an improvement in the Machine Translation system's performance by 5.64 and 9.91 BLEU points, for English-Marathi and Marathi-English, over the baseline model.
  arXiv  Detail & Related papers  (2023-12-18T16:06:18Z)
• Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting [32.70214938434769]
  We explore the ability of large language models (LLMs) to act as speech recognition post-processors. We evaluate different prompting schemes, both zero- and few-shot in-context learning, and a novel task activation prompting method. We show that rescoring only by in-context learning with frozen LLMs achieves results that are competitive with rescoring by domain-tuned LMs.
  arXiv  Detail & Related papers  (2023-09-27T13:36:03Z)
• Perturbation-based QE: An Explainable, Unsupervised Word-level Quality Estimation Method for Blackbox Machine Translation [12.376309678270275]
  Perturbation-based QE works simply by analyzing MT system output on perturbed input source sentences. Our approach is better at detecting gender bias and word-sense-disambiguation errors in translation than supervised QE.
  arXiv  Detail & Related papers  (2023-05-12T13:10:57Z)
• Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models [57.80514758695275]
  Using large language models (LLMs) for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level. We propose a new prompting method called textbftextttError Analysis Prompting (EAPrompt) This technique emulates the commonly accepted human evaluation framework - Multidimensional Quality Metrics (MQM) and textitproduces explainable and reliable MT evaluations at both the system and segment level.
  arXiv  Detail & Related papers  (2023-03-24T05:05:03Z)
• Ensemble Fine-tuned mBERT for Translation Quality Estimation [0.0]
  In this paper, we discuss our submission to the WMT 2021 QE Shared Task. Our proposed system is an ensemble of multilingual BERT (mBERT)-based regression models. It demonstrates comparable performance with respect to the Pearson's correlation and beats the baseline system in MAE/ RMSE for several language pairs.
  arXiv  Detail & Related papers  (2021-09-08T20:13:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.