Unified Open-Domain Question Answering with Structured and Unstructured Knowledge

by   Barlas Oguz, et al.

We study open-domain question answering (ODQA) with structured, unstructured and semi-structured knowledge sources, including text, tables, lists, and knowledge bases. Our approach homogenizes all sources by reducing them to text, and applies recent, powerful retriever-reader models which have so far been limited to text sources only. We show that knowledge-base QA can be greatly improved when reformulated in this way. Contrary to previous work, we find that combining sources always helps, even for datasets which target a single source by construction. As a result, our unified model produces state-of-the-art results on 3 popular ODQA benchmarks.


page 1

page 2

page 3

page 4


Open Domain Question Answering over Virtual Documents: A Unified Approach for Data and Text

Due to its potential for a universal interface over both data and text, ...

Question Answering from Unstructured Text by Retrieval and Comprehension

Open domain Question Answering (QA) systems must interact with external ...

A Graph Representation of Semi-structured Data for Web Question Answering

The abundant semi-structured data on the Web, such as HTML-based tables ...

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

We present the Open Predicate Query Language (OPQL); a method for constr...

Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds

Question Answering (QA), as a research field, has primarily focused on e...

Open Information Extraction on Scientific Text: An Evaluation

Open Information Extraction (OIE) is the task of the unsupervised creati...

Parser Extraction of Triples in Unstructured Text

The web contains vast repositories of unstructured text. We investigate ...