# A multi-task semi-supervised framework for Text2Graph & Graph2Text

arXiv: https://arxiv.org/abs/2202.06041 · HTML: https://mlsanity.com/paper/2202.06041/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 12 Feb 2022.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [A Survey on Knowledge Graph-Based Recommender Systems](https://mlsanity.com/paper/2003.00911/) (2020)
- [Learning From Noisy Large-Scale Datasets With Minimal Supervision](https://mlsanity.com/paper/1701.01619/) (2017)
- [CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training](https://mlsanity.com/paper/2006.04702/) (2020)

## Built on by (most cited first, 1 of 1)

- [Learning from Multiple Sources for Data-to-Text and Text-to-Data](https://mlsanity.com/paper/2302.11269/) (2023)

## Abstract (arXiv)

The Artificial Intelligence industry regularly develops applications that mostly rely on Knowledge Bases, a data repository about specific, or general, domains, usually represented in a graph shape. Similar to other databases, they face two main challenges: information ingestion and information retrieval. We approach these challenges by jointly learning graph extraction from text and text generation from graphs. The proposed solution, a T5 architecture, is trained in a multi-task semi-supervised environment, with our collected non-parallel data, following a cycle training regime. Experiments on WebNLG dataset show that our approach surpasses unsupervised state-of-the-art results in text-to-graph and graph-to-text. More relevantly, our framework is more consistent across seen and unseen domains than supervised models. The resulting model can be easily trained in any new domain with non-parallel data, by simply adding text and graphs about it, in our cycle framework.