# A Latent Variable Recurrent Neural Network for Discourse Relation Language Models

arXiv: https://arxiv.org/abs/1603.01913 · HTML: https://mlsanity.com/paper/1603.01913/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2016.

## Built on by (most cited first, 5 of 5)

- [Speaker Turn Modeling for Dialogue Act Classification](https://mlsanity.com/paper/2109.05056/) (2021)
- [Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media](https://mlsanity.com/paper/2105.01306/) (2021)
- [A Survey of Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2203.02982/) (2022)
- [Structured Dialogue Discourse Parsing](https://mlsanity.com/paper/2306.15103/) (2023)
- [Less is More: A Lightweight and Robust Neural Architecture for Discourse Parsing](https://mlsanity.com/paper/2210.09537/) (2022)

## Abstract (arXiv)

This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences. A recurrent neural network generates individual words, thus reaping the benefits of discriminatively-trained vector representations. The discourse relations are represented with a latent variable, which can be predicted or marginalized, depending on the task. The resulting model can therefore employ a training objective that includes not only discourse relation classification, but also word prediction. As a result, it outperforms state-of-the-art alternatives for two tasks: implicit discourse relation classification in the Penn Discourse Treebank, and dialog act classification in the Switchboard corpus. Furthermore, by marginalizing over latent discourse relations at test time, we obtain a discourse informed language model, which improves over a strong LSTM baseline.