Adaptive Information Seeking for Open-Domain Question Answering

09/14/2021
by   Yunchang Zhu, et al.
0

Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to be effective for complex questions, by recursively retrieving new evidence at each step. However, almost all existing iterative approaches use predefined strategies, either applying the same retrieval function multiple times or fixing the order of different retrieval functions, which cannot fulfill the diverse requirements of various questions. In this paper, we propose a novel adaptive information-seeking strategy for open-domain question answering, namely AISO. Specifically, the whole retrieval and answer process is modeled as a partially observed Markov decision process, where three types of retrieval operations (e.g., BM25, DPR, and hyperlink) and one answer operation are defined as actions. According to the learned policy, AISO could adaptively select a proper retrieval action to seek the missing evidence at each step, based on the collected evidence and the reformulated query, or directly output the answer when the evidence set is sufficient for the question. Experiments on SQuAD Open and HotpotQA fullwiki, which serve as single-hop and multi-hop open-domain QA benchmarks, show that AISO outperforms all baseline methods with predefined strategies in terms of both retrieval and answer evaluations.

READ FULL TEXT
research
06/15/2019

Multi-Hop Paragraph Retrieval for Open-Domain Question Answering

This paper is concerned with the task of multi-hop open-domain Question ...
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
12/07/2020

Conversational Browsing

How can we better understand the mechanisms behind multi-turn informatio...
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
05/14/2019

Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering

This paper introduces a new framework for open-domain question answering...
research
07/02/2020

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Generative models for open domain question answering have proven to be c...
research
09/27/2020

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

We propose a simple and efficient multi-hop dense retrieval approach for...

Please sign up or login with your details

Forgot password? Click here to reset