# Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translation

arXiv: https://arxiv.org/abs/1808.10432 · HTML: https://mlsanity.com/paper/1808.10432/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2018.

## Built on by (most cited first, 30 of 58)

- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset](https://mlsanity.com/paper/2205.12522/) (2022)
- [A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation](https://mlsanity.com/paper/2205.02022/) (2022)
- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [The Fallacy of AI Functionality](https://mlsanity.com/paper/2206.09511/) (2022)
- [Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation](https://mlsanity.com/paper/2102.00287/) (2021)
- [Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM](https://mlsanity.com/paper/2303.01911/) (2023)
- [Democratizing Neural Machine Translation with OPUS-MT](https://mlsanity.com/paper/2212.01936/) (2022)
- [Measuring and Increasing Context Usage in Context-Aware Machine Translation](https://mlsanity.com/paper/2105.03482/) (2021)
- [Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies](https://mlsanity.com/paper/2401.06760/) (2024)
- [The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail](https://mlsanity.com/paper/2110.08300/) (2021)
- [When Does Translation Require Context? A Data-driven, Multilingual Exploration](https://mlsanity.com/paper/2109.07446/) (2021)
- [A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism](https://mlsanity.com/paper/2401.05749/) (2024)
- [Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand](https://mlsanity.com/paper/2112.04139/) (2021)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs](https://mlsanity.com/paper/2410.18697/) (2024)
- [Do Context-Aware Translation Models Pay the Right Attention?](https://mlsanity.com/paper/2105.06977/) (2021)
- [GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation](https://mlsanity.com/paper/2101.06561/) (2021)
- [The statistical advantage of automatic NLG metrics at the system level](https://mlsanity.com/paper/2105.12437/) (2021)
- [Modeling Bilingual Conversational Characteristics for Neural Chat Translation](https://mlsanity.com/paper/2107.11164/) (2021)
- [Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers](https://mlsanity.com/paper/2108.00308/) (2021)
- [Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits](https://mlsanity.com/paper/2110.06997/) (2021)
- [Can Automatic Metrics Assess High-Quality Translations?](https://mlsanity.com/paper/2405.18348/) (2024)
- [Identifying Context-Dependent Translations for Evaluation Set Production](https://mlsanity.com/paper/2311.02321/) (2023)
- [Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification](https://mlsanity.com/paper/2109.07604/) (2021)
- [Towards Making the Most of Dialogue Characteristics for Neural Chat Translation](https://mlsanity.com/paper/2109.00668/) (2021)
- [Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance](https://mlsanity.com/paper/2205.02293/) (2022)
- [A Comparison of Approaches to Document-level Machine Translation](https://mlsanity.com/paper/2101.11040/) (2021)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)

## Abstract (arXiv)

We reassess a recent study (Hassan et al., 2018) that claimed that machine translation (MT) has reached human parity for the translation of news from Chinese into English, using pairwise ranking and considering three variables that were not taken into account in that previous study: the language in which the source side of the test set was originally written, the translation proficiency of the evaluators, and the provision of inter-sentential context. If we consider only original source text (i.e. not translated from another language, or translationese), then we find evidence showing that human parity has not been achieved. We compare the judgments of professional translators against those of non-experts and discover that those of the experts result in higher inter-annotator agreement and better discrimination between human and machine translations. In addition, we analyse the human translations of the test set and identify important translation issues. Finally, based on these findings, we provide a set of recommendations for future human evaluations of MT.