mlsanityData to 7 Oct 2026

Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task

arXiv 2210.09683 ↗First posted 18 Oct 2022cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies source-only, reference-only, and source-reference-combined evaluation scenarios into one single model. Specifically, during the model pre-training phase, we first apply the pseudo-labeled data examples to continuously pre-train UNITE. Notably, to reduce the gap between pre-training and fine-tuning, we use data cropping and a ranking-based score normalization strategy. During the fine-tuning phase, we use both Direct Assessment (DA) and Multidimensional Quality Metrics (MQM) data from past years' WMT competitions. Specially, we collect the results from models with different pre-trained language model backbones, and use different ensembling strategies for involved translation directions.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 16 of its 34 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

16 of 34 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  6. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  7. 2021Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translationcited by 333
  8. 2020InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Trainingcited by 237
  9. 2020TransQuest: Translation Quality Estimation with Cross-lingual Transformerscited by 59
  10. 2021Uncertainty-Aware Machine Translation Evaluationcited by 35
  11. 2022UniTE: Unified Translation Evaluationcited by 28
  12. 2020Self-Paced Learning for Neural Machine Translationcited by 27
4 more
  1. 2022Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translationcited by 13
  2. 2021Towards User-Driven Neural Machine Translationcited by 10
  3. 2022RoBLEURT Submission for the WMT2021 Metrics Taskcited by 9
  4. 2021KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generationcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 2.

7 papers.

  1. 2023GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4cited by 143
  2. 2024MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Taskcited by 92
  3. 2022ACES: Translation Accuracy Challenge Sets for Evaluating Machine Translation Metricscited by 25
  4. 2025Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progresscited by 10
  5. 2025Multi-task Adversarial Attacks against Black-box Model with Few-shot Queriescited by 1
  6. 2023Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluationcited by 0
  7. 2024Evaluating Automatic Metrics with Incremental Machine Translation Systemscited by 0