Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark

TL;DR

Universal NER v2 aims to develop a comprehensive, multilingual NER benchmark dataset to evaluate language models across diverse languages, addressing the scarcity of gold-standard evaluation resources.

Contribution

It extends the Universal NER project by creating standardized, cross-lingual NER datasets using a general tagset and annotation guidelines, fostering a collaborative community effort.

Findings

First installment (UNER v1) released in 2024

Ongoing expansion with diverse collaborators

Standardized annotations across multiple languages

Abstract

While multilingual language models promise to bring the benefits of LLMs to speakers of many languages, gold-standard evaluation benchmarks in most languages to interrogate these assumptions remain scarce. The Universal NER project, now entering its fourth year, is dedicated to building gold-standard multilingual Named Entity Recognition (NER) benchmark datasets. Inspired by existing massively multilingual efforts for other core NLP tasks (e.g., Universal Dependencies), the project uses a general tagset and thorough annotation guidelines to collect standardized, cross-lingual annotations of named entity spans. The first installment (UNER v1) was released in 2024, and the project has continued and expanded since then, with various organizers, annotators, and collaborators in an active community.