Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

06/12/2019
by   Yichen Jiang, et al.
0

Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble reader (EPAr). First, the Document Explorer iteratively selects relevant documents and represents divergent reasoning chains in a tree structure so as to allow assimilating information from all chains. The Answer Proposer then proposes an answer from every root-to-leaf path in the reasoning tree. Finally, the Evidence Assembler extracts a key sentence containing the proposed answer from every path and combines them to predict the final answer. Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. We jointly optimize our 3 modules by minimizing the sum of losses from each stage conditioned on the previous stage's output. On two multi-hop reading comprehension datasets WikiHop and MedHop, our EPAr model achieves significant improvements over the baseline and competitive results compared to the state-of-the-art model. We also present multiple reasoning-chain-recovery tests and ablation studies to demonstrate our system's ability to perform interpretable and accurate reasoning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/01/2019

Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents

Interpretable multi-hop reading comprehension (RC) over multiple documen...
research
11/02/2018

Exploiting Explicit Paths for Multi-hop Reading Comprehension

We focus on the task of multi-hop reading comprehension where a system i...
research
05/17/2019

Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Multi-hop reading comprehension (RC) across documents poses new challeng...
research
10/17/2017

Constructing Datasets for Multi-hop Reading Comprehension Across Documents

Most Reading Comprehension methods limit themselves to queries which can...
research
11/17/2021

Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction

Multi-hop QA with annotated supporting facts, which is the task of readi...
research
09/06/2018

Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks

Multi-hop reading comprehension focuses on one type of factoid question,...
research
07/25/2021

Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy

Multi-hop reading comprehension (MHRC) requires not only to predict the ...

Please sign up or login with your details

Forgot password? Click here to reset