Semantics Altering Modifications for Evaluating Comprehension in Machine Reading

Authors

  • Viktor Schlegel University of Manchester
  • Goran Nenadic University of Manchester
  • Riza Batista-Navarro University of Manchester

Keywords:

Question Answering, Interpretaility & Analysis of NLP Models, Adversarial Attacks & Robustness

Abstract

Advances in NLP have yielded impressive results for the task of machine reading comprehension (MRC), with approaches having been reported to achieve performance comparable to that of humans. In this paper, we investigate whether state-of-the-art MRC models are able to correctly process Semantics Altering Modifications (SAM): linguistically-motivated phenomena that alter the semantics of a sentence while preserving most of its lexical surface form. We present a method to automatically generate and align challenge sets featuring original and altered examples. We further propose a novel evaluation methodology to correctly assess the capability of MRC systems to process these examples independent of the data they were optimised on, by discounting for effects introduced by domain shift. In a large-scale empirical study, we apply the methodology in order to evaluate extractive MRC models with regard to their capability to correctly process SAM-enriched data. We comprehensively cover 12 different state-of-the-art neural architecture configurations and four training datasets and find that -- despite their well-known remarkable performance -- optimised models consistently struggle to correctly process semantically altered data.

Downloads

Published

2021-05-18

How to Cite

Schlegel, V., Nenadic, G., & Batista-Navarro, R. (2021). Semantics Altering Modifications for Evaluating Comprehension in Machine Reading. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13762-13770. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17622

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II