Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

09/17/2019
by   Ameya Godbole, et al.
0

Multi-hop question answering (QA) requires an information retrieval (IR) system that can find multiple supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to `hop' to other relevant evidence. In a setting, with more than 5 million Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by 10.59 F1.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2019

Latent Retrieval for Weakly Supervised Open Domain Question Answering

Recent work on open domain question answering (QA) assumes strong superv...
research
09/22/2020

Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering

Evidence retrieval is a key component of explainable question answering ...
research
10/10/2021

Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

Open-domain question answering answers a question based on evidence retr...
research
04/28/2023

Search-in-the-Chain: Towards Accurate, Credible and Traceable Large Language Models for Knowledge-intensive Tasks

With the wide application of Large Language Models (LLMs) such as ChatGP...
research
03/14/2022

Reasoning over Public and Private Data in Retrieval-Based Systems

Users and organizations are generating ever-increasing amounts of privat...
research
10/01/2019

Proximal Policy Optimization for Improved Convergence in IRGAN

IRGAN is an information retrieval (IR) modeling approach that uses a the...
research
09/17/2019

Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering

A key challenge of multi-hop question answering (QA) in the open-domain ...

Please sign up or login with your details

Forgot password? Click here to reset