Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering

02/07/2021
by   Nan Shao, et al.
0

Retrieving information from correlative paragraphs or documents to answer open-domain multi-hop questions is very challenging. To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose graph-based methods to retrieve them. However, in this paper, we point out the intrinsic defect of such methods. Instead, we propose a new architecture that models paragraphs as sequential data and considers multi-hop information retrieval as a kind of sequence labeling task. Specifically, we design a rewritable external memory to model the dependency among paragraphs. Moreover, a threshold gate mechanism is proposed to eliminate the distraction of noise paragraphs. We evaluate our method on both full wiki and distractor subtask of HotpotQA, a public textual multi-hop QA dataset requiring multi-hop information retrieval. Experiments show that our method achieves significant improvement over the published state-of-the-art method in retrieval and downstream QA task performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/12/2023

Performance Prediction for Multi-hop Questions

We study the problem of Query Performance Prediction (QPP) for open-doma...
research
09/16/2020

DDRQA: Dynamic Document Reranking for Open-domain Multi-hop Question Answering

Open-domain multi-hop question answering (QA) requires to retrieve multi...
research
10/15/2019

Answering Complex Open-domain Questions Through Iterative Query Generation

It is challenging for current one-step retrieve-and-read question answer...
research
11/24/2019

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

Answering questions that require multi-hop reasoning at web-scale necess...
research
04/27/2022

Generative Multi-hop Retrieval

Multi-hop retrieval is the task of retrieving a series of multiple docum...
research
12/10/2022

Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification

A key component of fact verification is thevevidence retrieval, often fr...
research
04/10/2022

Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering

Retrieval augmented language models have recently become the standard fo...

Please sign up or login with your details

Forgot password? Click here to reset