arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07951cs.CL
收藏

最佳规模-性能权衡:加权PoS标记器模型

Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Models

IT University of Copenhagen(哥本哈根信息技术大学)

Magnus Jacobsen, Mikkel H. Sørensen, Leon Derczynski

摘要:

基于机器学习的NLP性能的改进通常是通过更大的模型和更复杂的代码来呈现的。这是一个权衡:更好的分数是以更大的工具为代价的;更大的模型往往需要更多的训练和推理时间。我们提出了多种方法来测量模型的大小,并将其与模型的性能进行比较。在词性标注的案例研究中,我们将这些技术应用于八种语言的标注器,并提出了一种新的分析,确定哪些标注器是尺寸性能最佳的。结果表明,一些经典的标签的地方跨语言的大小性能的天际线。此外,尽管深度模型对于多个分数具有最高的性能,但通常不是这些模型中最复杂的模型达到峰值性能。

英文摘要:

Improvement in machine learning-based NLP performance are often presented with bigger models and more complex code. This presents a trade-off: better scores come at the cost of larger tools; bigger models tend to require more during training and inference time. We present multiple methods for measuring the size of a model, and for comparing this with the model's performance. In a case study over part-of-speech tagging, we then apply these techniques to taggers for eight languages and present a novel analysis identifying which taggers are size-performance optimal. Results indicate that some classical taggers place on the size-performance skyline across languages. Further, although the deep models have highest performance for multiple scores, it is often not the most complex of these that reach peak performance.

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。

↑