@inproceedings{meeus-etal-2024-msner,
title = "{MSNER}: A Multilingual Speech Dataset for Named Entity Recognition",
author = "Meeus, Quentin and
Moens, Marie-Francine and
Van hamme, Hugo",
editor = "Bunt, Harry and
Ide, Nancy and
Lee, Kiyong and
Petukhova, Volha and
Pustejovsky, James and
Romary, Laurent",
booktitle = "Proceedings of the 20th Joint ACL - ISO Workshop on Interoperable Semantic Annotation @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.isa-1.2",
pages = "8--16",
abstract = "While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by introducing MSNER, a freely available, multilingual speech corpus annotated with named entities. It provides annotations to the VoxPopuli dataset in four languages (Dutch, French, German, and Spanish). We have also releasing an efficient annotation tool that leverages automatic pre-annotations for faster manual refinement. This results in 590 and 15 hours of silver-annotated speech for training and validation, alongside a 17-hour, manually-annotated evaluation set. We further provide an analysis comparing silver and gold annotations. Finally, we present baseline NER models to stimulate further research on this newly available dataset.",
}
Markdown (Informal)
[MSNER: A Multilingual Speech Dataset for Named Entity Recognition](https://aclanthology.org/2024.isa-1.2) (Meeus et al., ISA-WS 2024)
ACL