Modern graph-based syntactic dependency parsers operate by predicting, for each token within a sentence, a probability distribution over its possible syntactic heads (i.e., all other tokens) and then extracting a maximum spanning tree from the resulting log-probabilities. Nowadays, virtually all such parsers utilize deep neural networks and may thus be susceptible to miscalibration (in particular, overconfident predictions). In this paper, we prove that temperature scaling, a popular technique for post-hoc calibration of neural networks, cannot change the output of the aforementioned procedure. We conclude that other techniques are needed to tackle miscalibration in graph-based dependency parsers in a way that improves parsing accuracy.
@article{arxiv.2106.08159,
title = {Maximum Spanning Trees Are Invariant to Temperature Scaling in Graph-based Dependency Parsing},
author = {Stefan Grünewald},
journal= {arXiv preprint arXiv:2106.08159},
year = {2021}
}