Skip to content
aiqbenchAI & Quantum Intelligence
NewsInsightsBenchmarksSkillsAsk AILearnAbout
...Loading your session
NewsInsightsBenchmarksSkillsAsk AILearnAbout
Back to list
aiqbench takeAI Products

aiqbench analysis

This study provides a critical discourse-sensitive evaluation of five commercial machine interpreting systems against human professionals in English-to-Chinese simultaneous translation, revealing that while top AI models can match human meaning scores in planned formal speeches, they fail significantly in spontaneous interviews due to semantic distortion and poor discourse tracking. The analysis highlights distinct error profiles where humans maintain communicative trajectories through contextual inference, whereas machines struggle with disfluency carryover and nonsensical output in unplanned settings.
1
Source coveringarXiv

Machine interpreting competitiveness: a discourse-sensitive comparison of meaning and target-language quality in English-Chinese simultaneous interpreting

arXiv·November 17, 2026·3 min read

From arXiv

Full text

arXiv:2611.19802v1 Announce Type: new Abstract: Machine interpreting (MI), or AI-enabled speech translation, is increasingly visible in professional and public-facing communication, yet its performance relative to human simultaneous interpreters remains insufficiently understood. Existing studies are often limited by a single discourse mode and evaluation frameworks that are not well aligned with interpreting as a discourse-level communicative activity. The present study compares five commercial MI systems with 26 human interpreters (14 professionals, 12 advanced students) on English-to-Chinese simultaneous interpreting across planned and unplanned discourse, focusing on meaning and target-language quality.

In these materials, MI performance differed sharply between the two discourse modes. In the planned formal speech, the strongest system became highly competitive on meaning, entering the upper human range, and a second system also performed strongly. In the extemporaneous interview, however, no MI system approached the stronger human tiers. Code-level analysis further shows that similar overall scores often masked different error profiles. Human interpreters were more likely to preserve the broader communicative trajectory through selective omission, restructuring, and contextual inference, whereas even the best MI systems were more vulnerable to semantic distortion, discourse-tracking failures, and context-insensitive interpretation.

On target-language quality, the human advantage proved more stable than on meaning. Unintelligible or nonsensical output and disfluency carryover emerge as particularly salient weaknesses in machine performance, especially in spontaneous discourse. Overall, the findings are consistent with a discourse-sensitive account of where MI appears competitive, where it remains limited, and why these distinctions matter for interpreting practice, interpreter education, and future MI development.

Abstract:Machine interpreting (MI), or AI-enabled speech translation, is increasingly visible in professional and public-facing communication, yet its performance relative to human simultaneous interpreters remains insufficiently understood. Existing studies are often limited by a single discourse mode and evaluation frameworks that are not well aligned with interpreting as a discourse-level communicative activity. The present study compares five commercial MI systems with 26 human interpreters (14 professionals, 12 advanced students) on English-to-Chinese simultaneous interpreting across planned and unplanned discourse, focusing on meaning and target-language quality.

In these materials, MI performance differed sharply between the two discourse modes. In the planned formal speech, the strongest system became highly competitive on meaning, entering the upper human range, and a second system also performed strongly. In the extemporaneous interview, however, no MI system approached the stronger human tiers. Code-level analysis further shows that similar overall scores often masked different error profiles. Human interpreters were more likely to preserve the broader communicative trajectory through selective omission, restructuring, and contextual inference, whereas even the best MI systems were more vulnerable to semantic distortion, discourse-tracking failures, and context-insensitive interpretation.

On target-language quality, the human advantage proved more stable than on meaning. Unintelligible or nonsensical output and disfluency carryover emerge as particularly salient weaknesses in machine performance, especially in spontaneous discourse. Overall, the findings are consistent with a discourse-sensitive account of where MI appears competitive, where it remains limited, and why these distinctions matter for interpreting practice, interpreter education, and future MI development.

88 pages, 4 figures, 5 tables. Includes Supplementary Information (40 pages)

Computation and Language (cs.CL)

arXiv:2611.19802 [cs.CL]

(or arXiv:2611.19802v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.19802 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Full text under the publisher's open licence · 350 words

Read at arXiv ↗Ask about this article

Article info

Source

arXiv

Published

November 17, 2026

Read time

3 min

Category

AI Products
aiqbench
AI & Quantum Intelligence© aiqbench. All rights reserved.

Feeds:RSS·JSON Feed

LanguageEnglish·Românăbeta
NewsAI & TechQuantumInsights
ExploreBenchmarksLearn
CompanyAboutTrustLegal noticeTerms of ServicePrivacy PolicyCopyright noticesData erasureReport content

The aiqbench take, the insights, the daily digest and Ask answers are written by AI models from the sources shown, without editorial review before publication. They may contain errors — check the source. How the model is used →

  • News
  • Insights
  • Ask AI
  • Benchmarks
  • Account