Appendix - Recommended Statistical Significance Tests for NLP Tasks

Published in arxiv, 2018

Recommended citation: "The Hitchhikers Guide to Testing Statistical Significance in Natural Language Processing." Rotem Dror, Gili Baumer, Segev Shlomov and Roi Reichart. Association for Computational Linguistics (ACL 2018).

Abstract Statistical significance testing plays an important role when drawing conclusions from experimental results in NLP papers. Particularly, it is a valuable tool when one would like to establish the superiority of one algorithm over another. Th is appendix complements the guide for testing statistical significance in NLP presented in Dror et al. (2018), by proposing valid statistical tests for the common tasks and evaluation measures in the field.