English(EN) How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups

机器翻译评估未能预测下游话语成功

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-15 11:44

一篇新的研究论文通过提出外在话语评估，探讨了当前机器翻译（MT）评估指标的局限性。该研究引入了一个实体计数任务来评估指称一致性，并使用福利外交游戏来评估互动环境中的沟通和协调。研究结果表明，高的内在MT质量并不能保证下游话语的成功，翻译失败会显著影响目标导向环境中的协调。 AI

影响强调了需要新的评估方法来捕捉机器翻译系统的实际性能。

排序理由该集群包含一篇在arXiv上发表的学术论文，详细介绍了评估机器翻译的新研究方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Wafaa Mohammed, Kata Naszadi, Vlad Niculae · 2026-06-16 04:00

How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups

arXiv:2606.16596v1 Announce Type: new Abstract: Existing machine translation (MT) metrics and discourse-focused evaluations primarily assess translation quality intrinsically, without measuring the downstream consequences of translation errors. In this work, we focus on extrinsic…
arXiv cs.CL TIER_1 English(EN) · Vlad Niculae · 2026-06-15 11:44

How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups

Existing machine translation (MT) metrics and discourse-focused evaluations primarily assess translation quality intrinsically, without measuring the downstream consequences of translation errors. In this work, we focus on extrinsic discourse evaluation of machine translation und…