arXiv cs.CL· Louis Est\`eve, Marie-Catherine de Marneffe, Nurit Melnik, Agata Savary, Olha Kanishcheva·· 12 小时前AI 评分20
NLP 多样性量化综述：为何、测什么、在哪测与怎么测
A survey of diversity quantification in natural language processing: The why, what, where and how
AI 导读
一项综述梳理 ACL Anthology 上 300 余篇多样性相关论文，提出面向 NLP 的四视角框架：为何重视多样性、测什么、在哪测、怎么测。研究发现 richness（最简单的 variety）与 distance averaging（最简单的 disparity）是最常见的度量族，纯 balance 度量几乎缺席，且 NLP 中半数度量不符合 Stirling 框架。
正文 · 原文
Abstract:The concept of diversity received increasing attention in natural language processing (NLP) in recent years. It became an advocated property of datasets and systems, with many measures used to quantify it, but also many cross-paper inconsistencies. To address this fragmentation, we take inspiration from other scientific fields where diversity has been more thoroughly conceptualized. We build upon (Sarkar, 2010) and (Stirling, 2007), two unified cross-domain frameworks inspired from ecology, economy and other domains. The first one advocates explicit justification of diversity endorsement. The latter distinguishes three dimensions of diversity: variety, balance, and disparity. Surveying over 300 recent diversity-related papers from ACL Anthology, we propose an NLP-specific framework with 4 perspectives: why diversity is important, what diversity is measured on, where it is measured, and how. We find that in NLP richness (the simplest variety) and distance averaging (the simplest disparity) are the most prevalent measure families, and that pure balance measures are nearly absent. Moreover, half of the measures used in NLP do not conform to Stirling's framework. Our analysis increases comparability of approaches to diversity in NLP, allowing us to formulate recommendations for the field. We recommend that the field systematically use a unified terminology, and that it engage in debates about the desirable properties of diversity measures as well as about the normative assumptions behind their use.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2507.20858 [cs.CL] |
| (or arXiv:2507.20858v4 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2507.20858 arXiv-issued DOI via DataCite |
Submission history
From: Louis Estève [view email]
[v1]
Mon, 28 Jul 2025 14:12:34 UTC (81 KB)
[v2]
Mon, 15 Dec 2025 11:50:31 UTC (93 KB)
[v3]
Fri, 13 Mar 2026 15:27:09 UTC (262 KB)
[v4]
Fri, 23 Oct 2026 08:31:38 UTC (406 KB)
来源：arXiv cs.CL · arxiv.org