《宪法说恩赫加图语:面向亚马逊通用语的开放机器翻译系统与可复现语料库流水线》
The Constitution Speaks Nheengatu: An Open MT System and Reproducible Corpus Pipeline for the Amazonian Língua Geral
AI总结:
本文针对亚马逊通用语恩赫加图语,构建了最大平行语料库、首个语音MT评估集及双向开放权重MT模型,发现语料扩展可提升语音翻译性能,NLLB模型对葡译恩赫加图语无增益,最终系统在三类测试集上达到对应chrF++指标。
摘要:
恩赫加图语(yrl)即亚马逊通用语,拥有6000至10000名使用者,在巴西圣加布里埃尔达卡舒埃拉市为共同官方语言,但目前经过评估的葡萄牙语-恩赫加图语机器翻译(MT)资源仍十分匮乏。本文介绍了为该语言构建的最大平行语料库(14500对葡萄牙语-恩赫加图语文本),以2023年巴西联邦宪法官方译本为核心;首个由转录自发语音构建的MT评估集;以及据本文所知,首个面向葡萄牙语-恩赫加图语双向翻译的开放权重MT模型。本文有三项核心发现:第一,在保留的宪法条款上进行恩赫加图语翻译时,无论训练时长或模型规模如何,开发数据上的性能均趋于平稳,剩余误差多来自书面语料未一致证实的常规法律术语;基于冻结词汇表的术语成功率显示,训练时的术语表机制与解码时的词汇约束均能提升术语实现率,后者会导致输出重复,但chrF++指标几乎未受影响。第二,添加转录对话的语料库扩展使语音chrF++提升24至27个点,同时书面领域性能保持不变,这种语域差异是仅书面基准无法察觉的。第三,更大规模的NLLB模型有助于葡萄牙语翻译,但对法律或语音文本的恩赫加图语翻译无帮助。对于葡萄牙语转恩赫加图语翻译,本文最终系统在条款不重叠的宪法文本上达到31.7至32.8的chrF++,近领域集上为64.1至64.5(移除目标侧内容重叠项后为62.1),语音文本上为45.2至47.5。
英文摘要:
Nheengatu (yrl), the Amazonian Língua Geral, has 6--10 thousand speakers and is co-official in São Gabriel da Cachoeira (Brazil), yet remains poorly served by evaluated Portuguese--Nheengatu MT resources. We present the largest parallel corpus assembled for the language (14.5k Portuguese--Nheengatu pairs), anchored by the 2023 official translation of the Brazilian Federal Constitution; the first MT evaluation set built from transcribed spontaneous speech; and, to our knowledge, the first open-weight MT models dedicated to bidirectional Portuguese--Nheengatu translation. Three findings organize the paper. First, translation into Nheengatu on held-out constitutional articles plateaus on development data regardless of training length or model size, and much of the remaining error sits in conventional legal terms that the written sources do not attest consistently; a terminology success rate over a frozen lexicon shows that glossary mechanisms at training time and lexical constraints at decoding each raise term realization, the latter at a cost in repetitive output that chrF++ barely registers. Second, a corpus expansion that adds transcribed conversation raises speech chrF++ by 24--27 points while leaving written domains unchanged, a register gap that written-only benchmarks cannot see. Third, a larger NLLB model helps translation into Portuguese but not into Nheengatu on legal or speech text. For Portuguese-to-Nheengatu translation, our final systems reach 31.7--32.8 chrF++ on article-disjoint constitutional text, 64.1--64.5 on the near-domain set (62.1 after removing items with target-side content overlap), and 45.2--47.5 on speech.
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。