In this paper, we introduce the Eval4NLP-2021shared task on explainable quality estimation. Given a source-translation pair, this shared task requires not only to provide a sentence-level score indicating the overall quality of the translation, but also to explain this score by identifying the words that negatively impact translation quality. We present the data, annotation guidelines and evaluation setup of the shared task, describe the six participating systems, and analyze the results. To the best of our knowledge, this is the first shared task on explainable NLP evaluation metrics. Datasets and results are available at https://github.com/eval4nlp/SharedTask2021.
@article{arxiv.2110.04392,
title = {The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results},
author = {Marina Fomicheva and Piyawat Lertvittayakumjorn and Wei Zhao and Steffen Eger and Yang Gao},
journal= {arXiv preprint arXiv:2110.04392},
year = {2021}
}