[论文] On the feasibility of dependency parsing of non-human sequences withou…

## 论文概要 **研究领域**: NLP **作者**: Ramon Ferrer-i-Cancho, Ca...

论文概要

研究领域: NLP 作者: Ramon Ferrer-i-Cancho, Catherine Hobaiter, Thore Bergman 发布时间: 2025-07-09 arXiv: 2507.06818

中文摘要

依存句法分析包括为序列寻找树表示。无监督依存句法分析旨在开发无需黄金标准即可在模型训练期间进行解析的方法。在人类语言中,无监督解析器可以被评估,因为通常可以获得或创建一些黄金标准。对于其他物种,黄金标准是未知的。因此,人们可能得出结论:确定无监督解析器的精度是不可能的,因此依存句法分析在其他物种中是不可行的。然而,在此我们应用网络科学的最新进展来证明,由于序列长度分布的快速衰减,解析器检索到的正确边的比例对于非人灵长类产生的发声或手势序列必须很高。相比之下,人类语言序列缺乏该属性。因此,在没有黄金标准的情况下,评估在非人灵长类中是可行的,但在人类中是一个难题。

原文摘要

Dependency parsing consists of finding a tree representation for a sequence. Unsupervised dependency parsing aims to develop parsing methods without a gold standard during model training. In human languages, an unsupervised parser can be evaluated because some gold standard is usually available or can be created. For other species, a gold standard is unknown. Thus one may conclude that it is impossible to determine the accuracy of an unsupervised parser and, consequently, dependency parsing is unfeasible in other species. However, here we apply recent advances in network science to demonstrate that the proportion of correct edges retrieved by a parser must be high for the sequences of vocalizations or gestures that non-human primates produce due to the fast decay of the sequence length dis…

自动采集于 2026-07-09

#论文 #arXiv #NLP #小凯

发表回复

人生梦想 - 关注前沿的计算机技术 acejoy.com 🐾 步子哥の博客 🐾 背多分论坛 🐾 借一步网 🐾 智柴网 沪ICP备2024052574号-1