English(EN) Your Embeddings Occupy a Narrow Cone. Cosine Similarity Assumes They Don’t.

BERT 嵌入占据狭窄锥体，挑战余弦相似度假设

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-04 13:01

最近的一项分析表明，平均池化的 BERT 嵌入在语义无关的配对之间表现出 0.99 的高余弦相似度。这种现象表明嵌入可能占据一个狭窄的锥体，这是标准余弦相似度指标无法解释的一个特征。该论文提出，这并不是检索系统中的错误，而是这些嵌入结构固有的属性。 AI

影响强调了衡量嵌入语义相似性方面的一个潜在局限性，影响检索和 NLP 任务。

排序理由学术论文，讨论嵌入和相似度指标的技术方面。[lever_c_demoted from research: ic=1 ai=1.0]

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

本文如何被排名

Signal score: 29 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，讨论嵌入和相似度指标的技术方面。[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。

Towards AI TIER_1 English(EN) · Aqeel Abbas · 2026-09-04 13:01

您的嵌入占据一个狭窄的锥形。余弦相似度假设它们不占据。

<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/your-embeddings-occupy-a-narrow-cone-cosine-similarity-assumes-they-dont-3fc9a367f6a1?source=rss----98111c9905da---4"><img src="https://cdn-images-1.medium.com/max/2600/0*4UJo2JsTKNlviLf…