# Database Reasoning Over Text

arXiv: https://arxiv.org/abs/2106.01074 · HTML: https://mlsanity.com/paper/2106.01074/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering](https://mlsanity.com/paper/1911.10470/) (2019)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Interpretation of Natural Language Rules in Conversational Machine Reading](https://mlsanity.com/paper/1809.01494/) (2018)
- [Neural Module Networks for Reasoning over Text](https://mlsanity.com/paper/1912.04971/) (2019)
- [Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension](https://mlsanity.com/paper/1909.00109/) (2019)
- [Quasar: Datasets for Question Answering by Search and Reading](https://mlsanity.com/paper/1707.03904/) (2017)
- [Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering](https://mlsanity.com/paper/1905.05733/) (2019)
- [Photon: A Robust Cross-Domain Text-to-SQL System](https://mlsanity.com/paper/2007.15280/) (2020)
- [Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training](https://mlsanity.com/paper/2010.12688/) (2020)

## Built on by (most cited first, 20 of 20)

- [FOLIO: Natural Language Reasoning with First-Order Logic](https://mlsanity.com/paper/2209.00840/) (2022)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs](https://mlsanity.com/paper/2205.12665/) (2022)
- [Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities](https://mlsanity.com/paper/2511.02817/) (2025)
- [Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills](https://mlsanity.com/paper/2107.07261/) (2021)
- [Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases](https://mlsanity.com/paper/2303.14617/) (2023)
- [The NLP Task Effectiveness of Long-Range Transformers](https://mlsanity.com/paper/2202.07856/) (2022)
- [Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data](https://mlsanity.com/paper/2410.11996/) (2024)
- [TimelineQA: A Benchmark for Question Answering over Timelines](https://mlsanity.com/paper/2306.01069/) (2023)
- [Compositional Generalization in Multilingual Semantic Parsing over Wikidata](https://mlsanity.com/paper/2108.03509/) (2021)
- [Multimodal Neural Databases](https://mlsanity.com/paper/2305.01447/) (2023)
- [RRAML: Reinforced Retrieval Augmented Machine Learning](https://mlsanity.com/paper/2307.12798/) (2023)
- [ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains](https://mlsanity.com/paper/2210.08763/) (2022)
- [DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?](https://mlsanity.com/paper/2406.12641/) (2024)
- [Prompt-to-OS (P2OS): Revolutionizing Operating Systems and Human-Computer Interaction with Integrated AI Generative Models](https://mlsanity.com/paper/2310.04875/) (2023)
- [Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables](https://mlsanity.com/paper/2304.13559/) (2023)
- [Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Database](https://mlsanity.com/paper/2305.14211/) (2023)
- [A Data Source for Reasoning Embodied Agents](https://mlsanity.com/paper/2309.07974/) (2023)
- [Machines & Influence: An Information Systems Lens](https://mlsanity.com/paper/2111.13365/) (2021)
- [Language Models That Walk the Talk: A Framework for Formal Fairness Certificates](https://mlsanity.com/paper/2505.12767/) (2025)

## Abstract (arXiv)

Neural models have shown impressive performance gains in answering queries from natural language text. However, existing works are unable to support database queries, such as "List/Count all female athletes who were born in 20th century", which require reasoning over sets of relevant facts with operations such as join, filtering and aggregation. We show that while state-of-the-art transformer models perform very well for small databases, they exhibit limitations in processing noisy data, numerical operations, and queries that aggregate facts. We propose a modular architecture to answer these database-style queries over multiple spans from text and aggregating these at scale. We evaluate the architecture using WikiNLDB, a novel dataset for exploring such queries. Our architecture scales to databases containing thousands of facts whereas contemporary models are limited by how many facts can be encoded. In direct comparison on small databases, our approach increases overall answer accuracy from 85% to 90%. On larger databases, our approach retains its accuracy whereas transformer baselines could not encode the context.