Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition

Mor Geva, Tomer Wolfson, Jonathan Berant

Research output: Contribution to journalArticlepeer-review

Abstract

Recent efforts to create challenge benchmarks that test the abilities of natural language understanding models have largely depended on human annotations. In this work, we introduce the ‘‘Break, Perturb, Build’’ (BPB) framework for automatic reasoning-oriented perturbation of question-answer pairs. BPB represents a question by decomposing it into the reasoning steps that are required to answer it, symbolically perturbs the decomposition, and then generates new question-answer pairs. We demonstrate the effectiveness of BPB by creating evaluation sets for three reading comprehension (RC) benchmarks, generating thousands of high-quality examples without human intervention. We evaluate a range of RC models on our evaluation sets, which reveals large performance gaps on generated examples compared to the original data. Moreover, symbolic perturbations enable fine-grained analysis of the strengths and limitations of models. Last, augmenting the training data with examples generated by BPB helps close the performance gaps, without any drop on the original data distribution.

Original languageEnglish
Pages (from-to)111-126
Number of pages16
JournalTransactions of the Association for Computational Linguistics
Volume10
DOIs
StatePublished - 9 Feb 2022

Funding

FundersFunder number
European Union Horizons 2020 research and innovation programmeDELPHI 802800
Yandex Initiative for Machine Learning
European Research Council

    Fingerprint

    Dive into the research topics of 'Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition'. Together they form a unique fingerprint.

    Cite this