Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering

08/22/2022
by   Siyuan Wang, et al.
0

Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable reasoning process. However, they ignore grounding on the supporting facts of each reasoning step, which tends to generate inaccurate decompositions. In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result. We employ a unified reader model for both intermediate hop reasoning and final hop inference and adopt joint optimization for more accurate and robust multi-hop reasoning. We conduct experiments on two benchmark datasets HotpotQA and 2WikiMultiHopQA. The results show that our method can effectively boost performance and also yields a better interpretable reasoning process without decomposition supervision.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2022

Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering

Effective multi-hop question answering (QA) requires reasoning over mult...
research
01/15/2018

An Interpretable Reasoning Network for Multi-Relation Question Answering

Multi-relation Question Answering is a challenging task, due to the requ...
research
02/27/2020

Generating Followup Questions for Interpretable Multi-hop Question Answering

We propose a framework for answering open domain multi-hop questions in ...
research
05/22/2020

A Complex KBQA System using Multiple Reasoning Paths

Multi-hop knowledge based question answering (KBQA) is a complex task fo...
research
01/02/2021

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval

Multi-hop reasoning (i.e., reasoning across two or more documents) at sc...
research
09/12/2019

Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning

Multi-hop QA requires a model to connect multiple pieces of evidence sca...
research
05/16/2019

Dynamically Fused Graph Network for Multi-hop Reasoning

Text-based question answering (TBQA) has been studied extensively in rec...

Please sign up or login with your details

Forgot password? Click here to reset