MultiMUC: Multilingual Template Filling on MUC-4

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gantt, William, Behzad, Shabnam, An, Hannah YoungEun, Chen, Yunmo, White, Aaron Steven, Van Durme, Benjamin, Yarmohammadi, Mahsa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909086016077824
author Gantt, William
Behzad, Shabnam
An, Hannah YoungEun
Chen, Yunmo
White, Aaron Steven
Van Durme, Benjamin
Yarmohammadi, Mahsa
author_facet Gantt, William
Behzad, Shabnam
An, Hannah YoungEun
Chen, Yunmo
White, Aaron Steven
Van Durme, Benjamin
Yarmohammadi, Mahsa
contents We introduce MultiMUC, the first multilingual parallel corpus for template filling, comprising translations of the classic MUC-4 template filling benchmark into five languages: Arabic, Chinese, Farsi, Korean, and Russian. We obtain automatic translations from a strong multilingual machine translation system and manually project the original English annotations into each target language. For all languages, we also provide human translations for sentences in the dev and test splits that contain annotated template arguments. Finally, we present baselines on MultiMUC both with state-of-the-art template filling models and with ChatGPT.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16209
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MultiMUC: Multilingual Template Filling on MUC-4
Gantt, William
Behzad, Shabnam
An, Hannah YoungEun
Chen, Yunmo
White, Aaron Steven
Van Durme, Benjamin
Yarmohammadi, Mahsa
Computation and Language
Artificial Intelligence
We introduce MultiMUC, the first multilingual parallel corpus for template filling, comprising translations of the classic MUC-4 template filling benchmark into five languages: Arabic, Chinese, Farsi, Korean, and Russian. We obtain automatic translations from a strong multilingual machine translation system and manually project the original English annotations into each target language. For all languages, we also provide human translations for sentences in the dev and test splits that contain annotated template arguments. Finally, we present baselines on MultiMUC both with state-of-the-art template filling models and with ChatGPT.
title MultiMUC: Multilingual Template Filling on MUC-4
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2401.16209