English

Multi-Dimensional Explanation of Target Variables from Documents

Computation and Language 2020-12-22 v4 Machine Learning

Abstract

Automated predictions require explanations to be interpretable by humans. Past work used attention and rationale mechanisms to find words that predict the target variable of a document. Often though, they result in a tradeoff between noisy explanations or a drop in accuracy. Furthermore, rationale methods cannot capture the multi-faceted nature of justifications for multiple targets, because of the non-probabilistic nature of the mask. In this paper, we propose the Multi-Target Masker (MTM) to address these shortcomings. The novelty lies in the soft multi-dimensional mask that models a relevance probability distribution over the set of target variables to handle ambiguities. Additionally, two regularizers guide MTM to induce long, meaningful explanations. We evaluate MTM on two datasets and show, using standard metrics and human annotations, that the resulting masks are more accurate and coherent than those generated by the state-of-the-art methods. Moreover, MTM is the first to also achieve the highest F1 scores for all the target variables simultaneously.

Keywords

Cite

@article{arxiv.1909.11386,
  title  = {Multi-Dimensional Explanation of Target Variables from Documents},
  author = {Diego Antognini and Claudiu Musat and Boi Faltings},
  journal= {arXiv preprint arXiv:1909.11386},
  year   = {2020}
}

Comments

Accepted in AAAI 2021. 18 pages, 14 figures, 9 tables

R2 v1 2026-06-23T11:25:15.665Z