arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.04216cs.CLcs.AI
收藏

2021年Dependency Pareto优化分析

A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021

Universidade da Coruña(拉科鲁尼亚大学);CITIC(信息与通信技术研究中心)

Mark Anderson, Carlos Gómez Rodríguez

摘要:

我们评估了三个领先的依赖解析器系统从不同的范式在一个小而多样的语言子集的准确性,效率的帕累托前。由于我们对效率感兴趣,我们评估了没有预先训练的语言模型的核心解析器(因为这些模型通常是巨大的网络,并且会构成大部分计算时间)或其他可以横向应用于其中任何一个的增强。Biaffine解析作为一个平衡的默认选择出现,如果推理速度(而不是训练能量成本)是优先级,则序列标记解析是首选。

英文摘要:

We evaluate three leading dependency parser systems from different paradigms on a small yet diverse subset of languages in terms of their accuracy-efficiency Pareto front. As we are interested in efficiency, we evaluate core parsers without pretrained language models (as these are typically huge networks and would constitute most of the compute time) or other augmentations that can be transversally applied to any of them. Biaffine parsing emerges as a well-balanced default choice, with sequence-labelling parsing being preferable if inference speed (but not training energy cost) is the priority.

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。

↑