Open Information Extraction from Question-Answer Pairs

TL;DR

NeurON is a novel system for extracting structured knowledge tuples from question-answer pairs, leveraging multi-source sequence-to-sequence learning to improve knowledge base extension from real-world data.

Contribution

It introduces a multi-source sequence-to-sequence approach for OpenIE from question-answer pairs, addressing challenges of understanding context and cross-sentence information.

Findings

NeurON outperforms state-of-the-art OpenIE methods on real-world datasets.

It extracts a significant number of new facts for knowledge base extension.

The approach effectively combines question and answer representations for better extraction.

Abstract

Open Information Extraction (OpenIE) extracts meaningful structured tuples from free-form text. Most previous work on OpenIE considers extracting data from one sentence at a time. We describe NeurON, a system for extracting tuples from question-answer pairs. Since real questions and answers often contain precisely the information that users care about, such information is particularly desirable to extend a knowledge base with. NeurON addresses several challenges. First, an answer text is often hard to understand without knowing the question, and second, relevant information can span multiple sentences. To address these, NeurON formulates extraction as a multi-source sequence-to-sequence learning task, wherein it combines distributed representations of a question and an answer to generate knowledge facts. We describe experiments on two real-world datasets that demonstrate that NeurON can find a significant number of new and interesting facts to extend a knowledge base compared to state-of-the-art OpenIE methods.