Multi-Dimensional Explanation of Target Variables from Documents

Diego Antognini, Claudiu Musat, Boi Faltings

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 explana-
tions 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 proba-
bility distribution over the set of target variables to handle
ambiguities. Additionally, two regularizers guide MTM to in-
duce 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.