@inproceedings{3414e12401754296bf7c7b2186af8feb,
title = "The Extended Dawid-Skene Model: Fusing Information from Multiple Data Schemas",
abstract = "While label fusion from multiple noisy annotations is a well understood concept in data wrangling (tackled for example by the Dawid-Skene (DS) model), we consider the extended problem of carrying out learning when the labels themselves are not consistently annotated with the same schema. We show that even if annotators use disparate, albeit related, label-sets, we can still draw inferences for the underlying full label-set. We propose the Inter-Schema AdapteR (ISAR) to translate the fully-specified label-set to the one used by each annotator, enabling learning under such heterogeneous schemas, without the need to re-annotate the data. We apply our method to a mouse behavioural dataset, achieving significant gains (compared with DS) in out-of-sample log-likelihood (−3.40 to −2.39) and F1-score (0.785 to 0.864).",
keywords = "Multi-schema learning, Crowdsourcing, Annotations, Behavioural characterisation, Probabilistic modelling, Data wrangling",
author = "Michael Camilleri and Williams, {Christopher K I}",
year = "2020",
month = mar,
day = "28",
doi = "10.1007/978-3-030-43823-4_11",
language = "English",
isbn = "978-3-030-43822-7",
series = "Communications in Computer and Information Science (CCIS)",
publisher = "Springer",
pages = "121--136",
editor = "Peggy Cellier and Kurt Driessens",
booktitle = "Machine Learning and Knowledge Discovery in Databases",
address = "United Kingdom",
note = "The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2019, ECMLPKDD 2019 ; Conference date: 16-09-2019 Through 20-09-2019",
}