# Unsupervised Inference of Data-Driven Discourse Structures using a Tree Auto-Encoder

arXiv: https://arxiv.org/abs/2210.09559 · HTML: https://mlsanity.com/paper/2210.09559/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 11 of 11)

- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [Tree-to-tree Neural Networks for Program Translation](https://mlsanity.com/paper/1802.03691/) (2018)
- [Learning to Compose Task-Specific Tree Structures](https://mlsanity.com/paper/1707.02786/) (2017)
- [Learning to Compose Words into Sentences with Reinforcement Learning](https://mlsanity.com/paper/1611.09100/) (2016)
- [A Hierarchical Neural Autoencoder for Paragraphs and Documents](https://mlsanity.com/paper/1506.01057/) (2015)
- [Neural Discourse Structure for Text Categorization](https://mlsanity.com/paper/1702.01829/) (2017)
- [Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs](https://mlsanity.com/paper/1705.09189/) (2017)
- [Evaluating Discourse in Structured Text Representations](https://mlsanity.com/paper/1906.01472/) (2019)
- [Predicting Discourse Structure using Distant Supervision from Sentiment](https://mlsanity.com/paper/1910.14176/) (2019)

## Abstract (arXiv)

With a growing need for robust and general discourse structures in many downstream tasks and real-world applications, the current lack of high-quality, high-quantity discourse trees poses a severe shortcoming. In order the alleviate this limitation, we propose a new strategy to generate tree structures in a task-agnostic, unsupervised fashion by extending a latent tree induction framework with an auto-encoding objective. The proposed approach can be applied to any tree-structured objective, such as syntactic parsing, discourse parsing and others. However, due to the especially difficult annotation process to generate discourse trees, we initially develop such method to complement task-specific models in generating much larger and more diverse discourse treebanks.