# Open Information Extraction from Question-Answer Pairs

arXiv: https://arxiv.org/abs/1903.00172 · HTML: https://mlsanity.com/paper/1903.00172/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

## Built on by (most cited first, 6 of 6)

- [A Survey on Neural Open Information Extraction: Current Status and Future Directions](https://mlsanity.com/paper/2205.11725/) (2022)
- [CompactIE: Compact Facts in Open Information Extraction](https://mlsanity.com/paper/2205.02880/) (2022)
- [MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extraction](https://mlsanity.com/paper/2308.06552/) (2023)
- [Part-of-Speech Tagger for Bodo Language using Deep Learning approach](https://mlsanity.com/paper/2401.03175/) (2024)
- [Answer Consolidation: Formulation and Benchmarking](https://mlsanity.com/paper/2205.00042/) (2022)
- [KGCQual: An Interpretable Framework for Evaluating the Knowledge Graph Construction Quality from Text](https://mlsanity.com/paper/2607.10212/) (2026)

## Abstract (arXiv)

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.