Do Multi-hop Readers Dream of Reasoning Chains?

by   Haoyu Wang, et al.

General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i.e. the ability to reason with information collected from multiple passages to derive the answer. In this paper we conduct a systematic analysis to assess such an ability of various existing models proposed for multi-hop QA tasks. Specifically, our analysis investigates that whether providing the full reasoning chain of multiple passages, instead of just one final passage where the answer appears, could improve the performance of the existing QA models. Surprisingly, when using the additional evidence passages, the improvements of all the existing multi-hop reading approaches are rather limited, with the highest error reduction of 5.8 to 1.3 To better understand whether the reasoning chains could indeed help find correct answers, we further develop a co-matching-based method that leads to 13.1 readers (including BERT). Our results demonstrate the existence of the potential improvement using explicit multi-hop reasoning and the necessity to develop models with better reasoning abilities.


page 1

page 2

page 3

page 4


Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Modern systems for multi-hop question answering (QA) typically break que...

Robustifying Multi-hop QA through Pseudo-Evidentiality Training

This paper studies the bias problem of multi-hop question answering mode...

Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering

Recent years have witnessed impressive advances in challenging multi-hop...

Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem

We introduce the task of implicit offensive text detection in dialogues,...

Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games

We propose the new problem of learning to recover reasoning chains from ...

Towards Teachable Reasoning Systems

Our goal is a teachable reasoning system for question-answering (QA), wh...

Counterfactual Variable Control for Robust and Interpretable Question Answering

Deep neural network based question answering (QA) models are neither rob...

Please sign up or login with your details

Forgot password? Click here to reset