← 研踪 PaperTrailarXiv:2611.11597 · v1
Out of Parameters, Saved by Syntax: UD-PrMPT for Parser Augmented Low Resource Machine Translation
首次提交 2026-11-09 04:24
版本更新 2026-11-09 04:24
雷达观测 2026-11-10 13:19
摘要
Recent work advancing machine translation quality using LLMs for very low resource languages has relied on the injection of lexicon-based prompt components to expose vocabulary to models. However, these approaches run into a ceiling when models must guess sentence meaning purely from plausible combinations of possible word senses mapped to strings. In this paper we test UD-PrMPT, an approach using syntactic analyses in the Universal Dependencies formalism as prompt components to improve MT in five diverse low resource languages: Beja, Chintang, Chukchi, Coptic, and Xibe. Our results show additive improvements which stack on top of the lexicon based approach which are stronger for higher quality manual analyses but consistent for predicted parses as well.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-09 04:24 · 最新观测版本
Out of Parameters, Saved by Syntax: UD-PrMPT for Parser Augmented Low Resource Machine Translation
Recent work advancing machine translation quality using LLMs for very low resource languages has relied on the injection of lexicon-based prompt components to expose vocabulary to models. However, these approaches run into a ceiling when models must guess sentence meaning purely from plausible combinations of possible word senses mapped to strings. In this paper we test UD-PrMPT, an approach using syntactic analyses in the Universal Dependencies formalism as prompt components to improve MT in five diverse low resource languages: Beja, Chintang, Chukchi, Coptic, and Xibe. Our results show additive improvements which stack on top of the lexicon based approach which are stronger for higher quality manual analyses but consistent for predicted parses as well.
查看此版本解读 →查看此版本原文 ↗