# Answering Complex Questions Using Open Information Extraction

arXiv: https://arxiv.org/abs/1704.05572 · HTML: https://mlsanity.com/paper/1704.05572/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2017.

## Built on by (most cited first, 25 of 25)

- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [Multi-Modal Answer Validation for Knowledge-Based VQA](https://mlsanity.com/paper/2103.12248/) (2021)
- [Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation](https://mlsanity.com/paper/2212.08632/) (2022)
- [UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text](https://mlsanity.com/paper/2108.08614/) (2021)
- [NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning](https://mlsanity.com/paper/2209.07662/) (2022)
- [DocOIE: A Document-level Context-Aware Dataset for OpenIE](https://mlsanity.com/paper/2105.04271/) (2021)
- [Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference](https://mlsanity.com/paper/2105.03417/) (2021)
- [AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark](https://mlsanity.com/paper/2109.07464/) (2021)
- [CompactIE: Compact Facts in Open Information Extraction](https://mlsanity.com/paper/2205.02880/) (2022)
- [Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder](https://mlsanity.com/paper/2210.06230/) (2022)
- [Easy-to-Hard Learning for Information Extraction](https://mlsanity.com/paper/2305.09193/) (2023)
- [When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications](https://mlsanity.com/paper/2211.08228/) (2022)
- [Encoding Explanatory Knowledge for Zero-shot Science Question Answering](https://mlsanity.com/paper/2105.05737/) (2021)
- [milIE: Modular & Iterative Multilingual Open Information Extraction](https://mlsanity.com/paper/2110.08144/) (2021)
- [Syntactic Multi-view Learning for Open Information Extraction](https://mlsanity.com/paper/2212.02068/) (2022)
- [PIE-QG: Paraphrased Information Extraction for Unsupervised Question Generation from Small Corpora](https://mlsanity.com/paper/2301.01064/) (2023)
- [Open Information Extraction via Chunks](https://mlsanity.com/paper/2305.03299/) (2023)
- [Efficient Data Learning for Open Information Extraction with Pre-trained Language Models](https://mlsanity.com/paper/2310.15021/) (2023)
- [Long-context Non-factoid Question Answering in Indic Languages](https://mlsanity.com/paper/2504.13615/) (2025)
- [Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers](https://mlsanity.com/paper/2208.03339/) (2022)
- [A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference](https://mlsanity.com/paper/2404.02625/) (2024)
- [Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?](https://mlsanity.com/paper/2509.25107/) (2025)
- [A Knowledge-based Approach for Answering Complex Questions in Persian](https://mlsanity.com/paper/2107.02040/) (2021)
- [Shall We Trust All Relational Tuples by Open Information Extraction? A Study on Speculation Detection](https://mlsanity.com/paper/2305.04181/) (2023)
- [Rules still work for Open Information Extraction](https://mlsanity.com/paper/2403.10758/) (2024)

## Abstract (arXiv)

While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques. Open Information Extraction (Open IE) provides a way to generate semi-structured knowledge for QA, but to date such knowledge has only been used to answer simple questions with retrieval-based methods. We overcome this limitation by presenting a method for reasoning with Open IE knowledge, allowing more complex questions to be handled. Using a recently proposed support graph optimization framework for QA, we develop a new inference model for Open IE, in particular one that can work effectively with multiple short facts, noise, and the relational structure of tuples. Our model significantly outperforms a state-of-the-art structured solver on complex questions of varying difficulty, while also removing the reliance on manually curated knowledge.