@inproceedings{41b8fa126bc140edb7474cce9156fa72,
title = "MuLER: Detailed and Scalable Reference-based Evaluation",
abstract = "We propose a novel methodology (namely, MuLER) that transforms any reference-based evaluation metric for text generation, such as machine translation (MT) into a fine-grained analysis tool. Given a system and a metric, MuLER quantifies how much the chosen metric penalizes specific error types (e.g., errors in translating names of locations). MuLER thus enables a detailed error analysis which can lead to targeted improvement efforts for specific phenomena. We perform experiments in both synthetic and naturalistic settings to support MuLER{\textquoteright}s validity and showcase its usability in MT evaluation, and other tasks, such as summarization. Analyzing all submissions to WMT in 2014−2020, we find consistent trends. For example, nouns and verbs are among the most frequent POS tags. However, they are among the hardest to translate. Performance on most POS tags improves with overall system performance, but a few are not thus correlated (their identity changes from language to language). Preliminary experiments with summarization reveal similar trends.1",
author = "Taelin Karidi and Gal Patel and Leshem Choshen and Omri Abend",
note = "Publisher Copyright: {\textcopyright} 2023 CoNLL 2023 - 27th Conference on Computational Natural Language Learning, Proceedings. All rights reserved.; 27th Conference on Computational Natural Language Learning, CoNLL 2023 ; Conference date: 06-12-2023 Through 07-12-2023",
year = "2023",
doi = "10.18653/v1/2023.conll-1.29",
language = "الإنجليزيّة",
series = "CoNLL 2023 - 27th Conference on Computational Natural Language Learning, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "436--455",
editor = "Jing Jiang and David Reitter and Shumin Deng",
booktitle = "CoNLL 2023 - 27th Conference on Computational Natural Language Learning, Proceedings",
address = "الولايات المتّحدة",
}