Semantics Altering Modifications for Evaluating Comprehension in Machine Reading

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.
Original languageEnglish
Title of host publicationAAAI 21: Proceedings of the 35th AAAI Conference
PublisherAssociation for the Advancement of Artificial Intelligence
Number of pages7
VolumeProceedings of the 35th AAAI Conference
Publication statusAccepted/In press - 1 Dec 2020

Fingerprint

Dive into the research topics of 'Semantics Altering Modifications for Evaluating Comprehension in Machine Reading'. Together they form a unique fingerprint.

Cite this