Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning

Tommaso Fornaciari, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, Massimo Poesio

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


Supervised learning assumes that a ground truth label exists. However, the reliability of this ground truth depends on human annotators, who often disagree. Prior work has shown that this disagreement can be helpful in training models. We propose a novel method to incorporate this disagreement as information: in addition to the standard error computation, we use soft labels (i.e., probability distributions over the annotator labels) as an auxiliary task in a multi-task neural network. We measure the divergence between the predictions and the target soft labels with several loss-functions and evaluate the models on various NLP tasks. We find that the soft-label pre- diction auxiliary task reduces the penalty for errors on ambiguous entities and thereby mitigates overfitting. It significantly improves performance across tasks beyond the standard approach and prior work.
Original languageEnglish
Title of host publicationProceedings of NAACL
PublisherAssociation for Computational Linguistics
Publication date2021
Publication statusPublished - 2021


  • Supervised Learning
  • Ground Truth Reliability
  • Human Annotator Disagreement
  • Soft Labels
  • Multi-task Neural Networks


Dive into the research topics of 'Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning'. Together they form a unique fingerprint.

Cite this