# Weakly Supervised Concept Map Generation through Task-Guided Graph Translation

arXiv: https://arxiv.org/abs/2110.15720 · HTML: https://mlsanity.com/paper/2110.15720/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 8 Oct 2021.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation](https://mlsanity.com/paper/2001.09382/) (2020)
- [GRAND: Graph Neural Diffusion](https://mlsanity.com/paper/2106.10934/) (2021)
- [GraphDF: A Discrete Flow Model for Molecular Graph Generation](https://mlsanity.com/paper/2102.01189/) (2021)
- [Modeling Coverage for Neural Machine Translation](https://mlsanity.com/paper/1601.04811/) (2016)
- [Learning Multimodal Graph-to-Graph Translation for Molecular Optimization](https://mlsanity.com/paper/1812.01070/) (2018)
- [Automated Phrase Mining from Massive Text Corpora](https://mlsanity.com/paper/1702.04457/) (2017)
- [Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples](https://mlsanity.com/paper/1805.06556/) (2018)
- [Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT](https://mlsanity.com/paper/1908.04943/) (2019)
- [Semi-Supervised Graph-to-Graph Translation](https://mlsanity.com/paper/2103.08827/) (2021)
- [Concept Pointer Network for Abstractive Summarization](https://mlsanity.com/paper/1910.08486/) (2019)
- [Deep Graph Translation](https://mlsanity.com/paper/1805.09980/) (2018)
- [Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps](https://mlsanity.com/paper/1704.04452/) (2017)
- [Evaluation of Unsupervised Entity and Event Salience Estimation](https://mlsanity.com/paper/2104.06924/) (2021)
- [Query-Specific Knowledge Summarization with Entity Evolutionary Networks](https://mlsanity.com/paper/1909.13183/) (2019)

## Built on by (most cited first, 2 of 2)

- [HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting](https://mlsanity.com/paper/2304.05973/) (2023)
- [Closed-book Question Generation via Contrastive Learning](https://mlsanity.com/paper/2210.06781/) (2022)

## Abstract (arXiv)

Recent years have witnessed the rapid development of concept map generation techniques due to their advantages in providing well-structured summarization of knowledge from free texts. Traditional unsupervised methods do not generate task-oriented concept maps, whereas deep generative models require large amounts of training data. In this work, we present GT-D2G (Graph Translation-based Document To Graph), an automatic concept map generation framework that leverages generalized NLP pipelines to derive semantic-rich initial graphs, and translates them into more concise structures under the weak supervision of downstream task labels. The concept maps generated by GT-D2G can provide interpretable summarization of structured knowledge for the input texts, which are demonstrated through human evaluation and case studies on three real-world corpora. Further experiments on the downstream task of document classification show that GT-D2G beats other concept map generation methods. Moreover, we specifically validate the labeling efficiency of GT-D2G in the label-efficient learning setting and the flexibility of generated graph sizes in controlled hyper-parameter studies.