自动搜索适合多语种形态复杂语言的神经网络结构
MorphNAS: Differentiable Architecture Search for Morphologically-Aware Multilingual NER
- 用语言学特征指导神经架构搜索，适配不同书写系统和形态复杂度
- 在多语种命名实体识别任务中显著提升性能，尤其对印度多文字语言有效
- 适合需要处理复杂形态语言的多语言NLP研究与应用
形态复杂的语言，特别是多书写系统的印度语言，给自然语言处理带来了重大挑战。本文提出MorphNAS，一种新颖的可微神经架构搜索框架，旨在应对这些挑战。MorphNAS通过引入如书写类型和形态复杂度等语言学元特征，改进可微架构搜索（DARTS），以优化命名实体识别（NER）的神经架构。该方法能自动识别针对语言特定形态特征的最优微观结构组件。通过自动化搜索过程，MorphNAS致力于提升多语言NLP模型的能力，从而增强对这些复杂语言的理解与处理效果。
原文摘要 · Abstract (English)
Morphologically complex languages, particularly multiscript Indian languages, present significant challenges for Natural Language Processing (NLP). This work introduces MorphNAS, a novel differentiable neural architecture search framework designed to address these challenges. MorphNAS enhances Differentiable Architecture Search (DARTS) by incorporating linguistic meta-features such as script type and morphological complexity to optimize neural architectures for Named Entity Recognition (NER). It automatically identifies optimal micro-architectural elements tailored to language-specific morphology. By automating this search, MorphNAS aims to maximize the proficiency of multilingual NLP models, leading to improved comprehension and processing of these complex languages.
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。