# Generating Diverse Descriptions from Semantic Graphs

arXiv: https://arxiv.org/abs/2108.05659 · HTML: https://mlsanity.com/paper/2108.05659/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 12 Aug 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [Comparison of Diverse Decoding Methods from Conditional Language Models](https://mlsanity.com/paper/1906.06362/) (2019)
- [Grammar as a Foreign Language](https://mlsanity.com/paper/1412.7449/) (2014)
- [Graph-to-Sequence Learning using Gated Graph Neural Networks](https://mlsanity.com/paper/1806.09835/) (2018)
- [Neural AMR: Sequence-to-Sequence Models for Parsing and Generation](https://mlsanity.com/paper/1704.08381/) (2017)
- [Neural data-to-text generation: A comparison between pipeline and end-to-end architectures](https://mlsanity.com/paper/1908.09022/) (2019)
- [Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks](https://mlsanity.com/paper/1804.00823/) (2018)
- [Variational Neural Machine Translation](https://mlsanity.com/paper/1605.07869/) (2016)
- [Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2001.11003/) (2020)
- [Deep Graph Convolutional Encoders for Structured Data to Text Generation](https://mlsanity.com/paper/1810.09995/) (2018)
- [Neural Generative Question Answering](https://mlsanity.com/paper/1512.01337/) (2015)
- [Conditional Variational Autoencoder for Neural Machine Translation](https://mlsanity.com/paper/1812.04405/) (2018)
- [A Stochastic Decoder for Neural Machine Translation](https://mlsanity.com/paper/1805.10844/) (2018)

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

- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)

## Abstract (arXiv)

Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting lexical, syntactic and semantic variation. To address this disconnect, we present two main contributions. First, we propose a stochastic graph-to-text model, incorporating a latent variable in an encoder-decoder model, and its use in an ensemble. Second, to assess the diversity of the generated sentences, we propose a new automatic evaluation metric which jointly evaluates output diversity and quality in a multi-reference setting. We evaluate the models on WebNLG datasets in English and Russian, and show an ensemble of stochastic models produces diverse sets of generated sentences, while retaining similar quality to state-of-the-art models.