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.- Anthology ID:
- 2021.bppf-1.2
- Volume:
- Proceedings of the 1st Workshop on Benchmarking: Past, Present and Future
- Month:
- Aug
- Year:
- 2021
- Address:
- Online
- Venue:
- BPPF
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8–14
- Language:
- URL:
- https://aclanthology.org/2021.bppf-1.2
- DOI:
- 10.18653/v1/2021.bppf-1.2
- Cite (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.
- Cite (Informal):
- Guideline Bias in Wizard-of-Oz Dialogues (Hansen & Søgaard, BPPF 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.bppf-1.2.pdf
- Code
- vpetren/guideline_bias
- Data
- CCPE-M, Taskmaster-1