# DualTKB: A Dual Learning Bridge between Text and Knowledge Base

arXiv: https://arxiv.org/abs/2010.14660 · HTML: https://mlsanity.com/paper/2010.14660/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models](https://mlsanity.com/paper/2108.12472/) (2021)
- [Knowledge Graph Generation From Text](https://mlsanity.com/paper/2211.10511/) (2022)
- [Autoregressive Entity Generation for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2209.08708/) (2022)
- [Open Relation Modeling: Learning to Define Relations between Entities](https://mlsanity.com/paper/2108.09241/) (2021)
- [DEER: Descriptive Knowledge Graph for Explaining Entity Relationships](https://mlsanity.com/paper/2205.10479/) (2022)
- [DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization](https://mlsanity.com/paper/2508.14460/) (2025)
- [Unsupervised Term Extraction for Highly Technical Domains](https://mlsanity.com/paper/2210.13118/) (2022)
- [Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction](https://mlsanity.com/paper/2401.10189/) (2024)

## Abstract (arXiv)

In this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs). We investigate the impact of weak supervision by creating a weakly supervised dataset and show that even a slight amount of supervision can significantly improve the model performance and enable better-quality transfers. We examine different model architectures, and evaluation metrics, proposing a novel Commonsense KB completion metric tailored for generative models. Extensive experimental results show that the proposed method compares very favorably to the existing baselines. This approach is a viable step towards a more advanced system for automatic KB construction/expansion and the reverse operation of KB conversion to coherent textual descriptions.