@inproceedings{hansen-sogaard-2021-guideline,
title = "Guideline Bias in {W}izard-of-{O}z Dialogues",
author = "Hansen, Victor Petr{\'e}n Bach and
S{\o}gaard, Anders",
editor = "Church, Kenneth and
Liberman, Mark and
Kordoni, Valia",
booktitle = "Proceedings of the 1st Workshop on Benchmarking: Past, Present and Future",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bppf-1.2",
doi = "10.18653/v1/2021.bppf-1.2",
pages = "8--14",
abstract = "NLP models struggle with generalization due to sampling and annotator bias. This paper focuses on a different kind of bias that has received very little attention: guideline bias, i.e., the bias introduced by how our annotator guidelines are formulated. We examine two recently introduced dialogue datasets, CCPE-M and Taskmaster-1, both collected by trained assistants in a Wizard-of-Oz set-up. For CCPE-M, we show how a simple lexical bias for the word like in the guidelines biases the data collection. This bias, in effect, leads to poor performance on data without this bias: a preference elicitation architecture based on BERT suffers a 5.3{\%} absolute drop in performance, when like is replaced with a synonymous phrase, and a 13.2{\%} drop in performance when evaluated on out-of-sample data. For Taskmaster-1, we show how the order in which instructions are resented, biases the data collection.",
}
Markdown (Informal)
[Guideline Bias in Wizard-of-Oz Dialogues](https://aclanthology.org/2021.bppf-1.2) (Hansen & Søgaard, BPPF 2021)
ACL
- Victor Petrén Bach Hansen and Anders Søgaard. 2021. Guideline Bias in Wizard-of-Oz Dialogues. In Proceedings of the 1st Workshop on Benchmarking: Past, Present and Future, pages 8–14, Online. Association for Computational Linguistics.