Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval

04/13/2021
by   Chen Zhao, et al.
0

Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2023

Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Database

In Textual question answering (TQA) systems, complex questions often req...
research
06/15/2021

Analysing Dense Passage Retrieval for Multi-hop Question Answering

We analyse the performance of passage retrieval models in the presence o...
research
04/15/2020

HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data

Existing question answering datasets focus on dealing with homogeneous i...
research
10/17/2022

ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains

The ability of reasoning over evidence has received increasing attention...
research
05/31/2023

Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data

This paper presents Structure Aware Dense Retrieval (SANTA) model, which...
research
04/20/2016

Question Answering via Integer Programming over Semi-Structured Knowledge

Answering science questions posed in natural language is an important AI...
research
08/17/2023

Beam Retrieval: General End-to-End Retrieval for Multi-Hop Question Answering

Multi-hop QA involves finding multiple relevant passages and step-by-ste...

Please sign up or login with your details

Forgot password? Click here to reset