BriefGPT.xyz
Mar, 2024
利用背景信息进行句子级词素切割
Using Contextual Information for Sentence-level Morpheme Segmentation
HTML
PDF
Prabin Bhandari, Abhishek Paudel
TL;DR
通过将整个句子作为输入，我们将形态素分割任务重新定义为序列到序列问题，结果显示多语种模型在性能上优于单语种模型，尽管没有超过最先进性能，但与高资源语言相比展现出了可比较的效果，同时揭示了在低资源语言情境下的限制。
Abstract
Recent advancements in
morpheme segmentation
primarily emphasize word-level segmentation, often neglecting the
contextual relevance
within the sentence. In this study, we redefine the
→