arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.03008cs.CLcs.AI
收藏

平衡全局质量与代词特定反馈的上下文感知机器翻译

Balancing Global Quality and Pronoun-Specific Feedback for Context-Aware Machine Translation

Indian Institute of Technology Patna(印度理工学院巴特那分校);Indian Institute of Technology Jodhpur(印度理工学院焦特布尔分校)

Harshit Dhankhar, Baban Gain, Asif Ekbal, Yogesh Mani Tripathi

AI总结:

本文提出ProNMT,一种结合全局质量与代词置信度反馈的迭代自训练方法,在上下文感知翻译中提升BLEU和COMET,表明针对性反馈需与全局信号及上下文结合才有效。

摘要:

上下文感知的机器翻译可以揭示代词选择所需的证据,但标准的微调并未明确优先处理这些稀疏的话语敏感决策。我们研究了ProNMT,一种奖励引导的迭代自训练方法,它将句子级质量估计与生成代词位置上的带符号置信度信号相结合。对于每个当前句子及其前面的源上下文,ProNMT采样候选翻译,使用无参考质量估计和从参考中导出的代词标签对它们进行评分,并在得分最高的候选上进行微调。在过滤后的英语-德语Europarl和英语-法语新闻评论数据上,ProNMT在BLEU和COMET指标上优于上下文感知的监督微调。消融实验表明,仅代词反馈会严重降低这些以代词为中心的数据上的句子级翻译质量,而硬二元反馈的性能不如置信度加权反馈。这些结果表明,当针对性的语言反馈与全局质量信号和与目标决策相关的上下文相结合时,最为有效。我们在此https URL公开提供代码。

英文摘要:

Context-aware machine translation can expose the evidence needed for pronoun choice, but standard fine-tuning does not explicitly prioritize these sparse discourse-sensitive decisions. We study ProNMT, a reward-guided iterative self-training method that combines sentence-level quality estimation with a signed confidence signal at generated pronoun positions. For each current sentence and its preceding source context, ProNMT samples candidate translations, scores them using reference-free quality estimation together with a reference-derived pronoun label, and fine-tunes on the highest-scoring candidate. On filtered English--German Europarl and English--French News Commentary data, ProNMT improves over context-aware supervised fine-tuning on BLEU and COMET. Ablations show that pronoun-only feedback can severely degrade sentence-level translation quality on these pronoun-focused data, while hard binary feedback underperforms confidence-weighted feedback. These results indicate that targeted linguistic feedback is most useful when combined with both a global quality signal and the context relevant to the targeted decision. We make the code publicly available at https://github.com/Harshit2807161/ProNMT.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑