# CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases

arXiv: https://arxiv.org/abs/1606.01994 · HTML: https://mlsanity.com/paper/1606.01994/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2016.

## Built on by (most cited first, 12 of 12)

- [An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.10368/) (2023)
- [Prix-LM: Pretraining for Multilingual Knowledge Base Construction](https://mlsanity.com/paper/2110.08443/) (2021)
- [Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge](https://mlsanity.com/paper/2104.05216/) (2021)
- [Evaluation of Question Answering Systems: Complexity of judging a natural language](https://mlsanity.com/paper/2209.12617/) (2022)
- [Binder: Hierarchical Concept Representation through Order Embedding of Binary Vectors](https://mlsanity.com/paper/2404.10924/) (2024)
- [EXTRACT: Explainable Transparent Control of Bias in Embeddings](https://mlsanity.com/paper/2311.00115/) (2023)
- [Incremental Knowledge Based Question Answering](https://mlsanity.com/paper/2101.06938/) (2021)
- [Knowledge Graph Question Answering via SPARQL Silhouette Generation](https://mlsanity.com/paper/2109.09475/) (2021)
- [Semantic Parsing for Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2401.06772/) (2023)
- [Knowledge Fusion via Bidirectional Information Aggregation](https://mlsanity.com/paper/2507.08704/) (2025)
- [Towards Collaborative Question Answering: A Preliminary Study](https://mlsanity.com/paper/2201.09708/) (2022)
- [Question Answering Over Spatio-Temporal Knowledge Graph](https://mlsanity.com/paper/2402.11542/) (2024)

## Abstract (arXiv)

How can we enable computers to automatically answer questions like "Who created the character Harry Potter"? Carefully built knowledge bases provide rich sources of facts. However, it remains a challenge to answer factoid questions raised in natural language due to numerous expressions of one question. In particular, we focus on the most common questions --- ones that can be answered with a single fact in the knowledge base. We propose CFO, a Conditional Focused neural-network-based approach to answering factoid questions with knowledge bases. Our approach first zooms in a question to find more probable candidate subject mentions, and infers the final answers with a unified conditional probabilistic framework. Powered by deep recurrent neural networks and neural embeddings, our proposed CFO achieves an accuracy of 75.7% on a dataset of 108k questions - the largest public one to date. It outperforms the current state of the art by an absolute margin of 11.8%.