# Complex Factoid Question Answering with a Free-Text Knowledge Graph

arXiv: https://arxiv.org/abs/2103.12876 · HTML: https://mlsanity.com/paper/2103.12876/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text](https://mlsanity.com/paper/1809.00782/) (2018)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Simple and Effective Multi-Paragraph Reading Comprehension](https://mlsanity.com/paper/1710.10723/) (2017)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [Dynamically Fused Graph Network for Multi-hop Reasoning](https://mlsanity.com/paper/1905.06933/) (2019)
- [Question Answering with Subgraph Embeddings](https://mlsanity.com/paper/1406.3676/) (2014)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs](https://mlsanity.com/paper/1905.07374/) (2019)
- [Efficient and Robust Question Answering from Minimal Context over Documents](https://mlsanity.com/paper/1805.08092/) (2018)
- [Question Answering is a Format; When is it Useful?](https://mlsanity.com/paper/1909.11291/) (2019)
- [Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs](https://mlsanity.com/paper/1908.00469/) (2019)
- [Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering](https://mlsanity.com/paper/1901.00603/) (2019)
- [Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge](https://mlsanity.com/paper/1607.03542/) (2016)

## Built on by (most cited first, 14 of 14)

- [From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment](https://mlsanity.com/paper/2109.02363/) (2021)
- [Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval](https://mlsanity.com/paper/2104.05883/) (2021)
- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Exploiting Reasoning Chains for Multi-hop Science Question Answering](https://mlsanity.com/paper/2109.02905/) (2021)
- [Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness](https://mlsanity.com/paper/2108.05278/) (2021)
- [ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains](https://mlsanity.com/paper/2210.08763/) (2022)
- [SHGNN: Structure-Aware Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2112.06244/) (2021)
- [Question Answering with Deep Neural Networks for Semi-Structured Heterogeneous Genealogical Knowledge Graphs](https://mlsanity.com/paper/2307.16214/) (2023)
- [Query-Specific Knowledge Graphs for Complex Finance Topics](https://mlsanity.com/paper/2211.04142/) (2022)
- [TIGER: Temporally Improved Graph Entity Linker](https://mlsanity.com/paper/2410.09128/) (2024)
- [Recent Advances in Automated Question Answering In Biomedical Domain](https://mlsanity.com/paper/2111.05937/) (2021)
- [Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts](https://mlsanity.com/paper/2407.15588/) (2024)
- [LiCQA : A Lightweight Complex Question Answering System](https://mlsanity.com/paper/2602.22182/) (2026)
- [Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey](https://mlsanity.com/paper/2607.09666/) (2026)

## Abstract (arXiv)

We introduce DELFT, a factoid question answering system which combines the nuance and depth of knowledge graph question answering approaches with the broader coverage of free-text. DELFT builds a free-text knowledge graph from Wikipedia, with entities as nodes and sentences in which entities co-occur as edges. For each question, DELFT finds the subgraph linking question entity nodes to candidates using text sentences as edges, creating a dense and high coverage semantic graph. A novel graph neural network reasons over the free-text graph-combining evidence on the nodes via information along edge sentences-to select a final answer. Experiments on three question answering datasets show DELFT can answer entity-rich questions better than machine reading based models, bert-based answer ranking and memory networks. DELFT's advantage comes from both the high coverage of its free-text knowledge graph-more than double that of dbpedia relations-and the novel graph neural network which reasons on the rich but noisy free-text evidence.