@inproceedings{dad568ae1c874300a0f52139d7e00c46,
title = "Evaluation Guidelines to Deal with Implicit Phenomena to Assess Factuality in Data-to-Text Generation",
abstract = "Data-to-text generation systems are trained on large datasets, such as WebNLG, RotoWire, E2E or DART. Beyond traditional token-overlap evaluation metrics (BLEU or METEOR), a key concern faced by recent generators is to control the factuality of the generated text with respect to the input data specification. We report on our experience when developing an automatic factuality evaluation system for data-to-text generation that we are testing on WebNLG and E2E data. We aim to prepare gold data annotated manually to identify cases where the text communicates more information than is warranted based on the input data (extra) or fails to communicate data that is part of the input (missing). While analyzing reference (data, text) samples, we encountered a range of systematic uncertainties that are related to cases on implicit phenomena in text, and the nature of non-linguistic knowledge we expect to be involved when assessing factuality. We derive from our experience a set of evaluation guidelines to reach high inter-annotator agreement on such cases.",
author = "Roy Eisenstadt and Michael Elhadad",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 1st Workshop on Understanding Implicit and Underspecified Language, UNIMPLICIT 2021 ; Conference date: 05-08-2021 Through 06-08-2021",
year = "2021",
month = jan,
day = "1",
language = "American English",
series = "UNIMPLICIT 2021 - 1st Workshop on Understanding Implicit and Underspecified Language, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "20--27",
editor = "Michael Roth and Reut Tsarfaty and Yoav Goldberg",
booktitle = "UNIMPLICIT 2021 - 1st Workshop on Understanding Implicit and Underspecified Language, Proceedings of the Workshop",
address = "United States",
}