用词素建模提升低资源语言自动标注效率与可解释性
CWoMP: Morpheme Representation Learning for Interlinear Glossing
- 将词素作为基本语义单元，通过对比学习构建联合表示空间
- 在低资源语言上超越现有方法，极端低资源下提升显著
- 支持运行时扩展词库，无需重训练即可改进结果
互线标注文本（IGT）是语言记录的标准形式，虽语义丰富但人工制作耗时。现有自动化方法将标注视为字符序列，忽略其构词结构。本文提出CWoMP（对比词-词素预训练），将词素视为原子形式-意义单元，通过对比训练编码器在共享嵌入空间中对齐上下文中的词与其构成词素；解码器则通过检索可变词典中的词素嵌入，自回归生成词素序列。预测结果具有可解释性，且用户可在推理时通过扩展词典优化性能而无需重新训练。在多种低资源语言上评估表明，CWoMP不仅显著优于现有方法，且效率更高，尤其在极低资源场景下表现突出。
原文摘要 · Abstract (English)
Interlinear glossed text (IGT) is a standard notation for language documentation which is linguistically rich but laborious to produce manually. Recent automated IGT methods treat glosses as character sequences, neglecting their compositional structure. We propose CWoMP (Contrastive Word-Morpheme Pretraining), which instead treats morphemes as atomic form-meaning units with learned representations. A contrastively trained encoder aligns words-in-context with their constituent morphemes in a shared embedding space; an autoregressive decoder then generates the morpheme sequence by retrieving entries from a mutable lexicon of these embeddings. Predictions are interpretable--grounded in lexicon entries--and users can improve results at inference time by expanding the lexicon without retraining. We evaluate on diverse low-resource languages, showing that CWoMP outperforms existing methods while being significantly more efficient, with particularly strong gains in extremely low-resource settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。