PulseAugur
中
实时 09:14:10
English(EN) P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing

新的P2TPO框架提高了全页文档解析的准确性

研究人员开发了一个名为页面到令牌策略优化(P2TPO)的新框架,旨在提高端到端全页文档解析的准确性。该方法通过将页面级质量评估与特定生成的跨度对齐,来解决文档分析中的局部错误和遗漏。P2TPO利用参考元素对齐、统一锚点定价和跨度信用重新分配来识别和纠正文档中的不准确之处,在多个基准测试中表现优于现有的策略优化基线。 AI

影响 提高了文档解析的准确性,可能有助于处理和分析大量文本的AI系统。

排序理由 详细介绍文档解析新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的P2TPO框架提高了全页文档解析的准确性

本文如何被排名

Signal score
14 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍文档解析新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Yong Zu, Ninghua Yang, Zezhong Tan, Xinhong Ma, Ziqiang Dong, Yang Yang ·

    P2TPO:结构对齐的页面到令牌信用分配,用于全页文档解析

    arXiv:2610.21979v1 Announce Type: cross Abstract: End-to-end full-page document parsing must preserve the content and structure of heterogeneous elements, yet otherwise accurate outputs can contain local errors and omissions. A single page-level advantage does not explicitly iden…