Multi-hop Reading Comprehension through Question Decomposition and Rescoring

06/07/2019
by   Sewon Min, et al.
2

Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question into simpler sub-questions that can be answered by off-the-shelf single-hop RC models. Since annotations for such decomposition are expensive, we recast sub-question generation as a span prediction problem and show that our method, trained using only 400 labeled examples, generates sub-questions that are as effective as human-authored sub-questions. We also introduce a new global rescoring approach that considers each decomposition (i.e. the sub-questions and their answers) to select the best final answer, greatly improving overall performance. Our experiments on HotpotQA show that this approach achieves the state-of-the-art results, while providing explainable evidence for its decision making in the form of sub-questions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/07/2022

Complex Reading Comprehension Through Question Decomposition

Multi-hop reading comprehension requires not only the ability to reason ...
research
06/07/2019

Compositional Questions Do Not Necessitate Multi-hop Reasoning

Multi-hop reading comprehension (RC) questions are challenging because t...
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
09/29/2019

Tag-based Multi-Span Extraction in Reading Comprehension

With models reaching human performance on many popular reading comprehen...
research
01/15/2021

Coarse-grained decomposition and fine-grained interaction for multi-hop question answering

Recent advances regarding question answering and reading comprehension h...
research
04/27/2019

Understanding Dataset Design Choices for Multi-hop Reasoning

Learning multi-hop reasoning has been a key challenge for reading compre...
research
10/16/2019

Why can't memory networks read effectively?

Memory networks have been a popular choice among neural architectures fo...

Please sign up or login with your details

Forgot password? Click here to reset