# Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction

arXiv: https://arxiv.org/abs/1704.01691 · HTML: https://mlsanity.com/paper/1704.01691/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2017.

## Built on by (most cited first, 9 of 9)

- [Transformer-based Conditional Variational Autoencoder for Controllable Story Generation](https://mlsanity.com/paper/2101.00828/) (2021)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Debiasing Learning for Membership Inference Attacks Against Recommender Systems](https://mlsanity.com/paper/2206.12401/) (2022)
- [Political Depolarization of News Articles Using Attribute-aware Word Embeddings](https://mlsanity.com/paper/2101.01391/) (2021)
- [Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting](https://mlsanity.com/paper/2404.12782/) (2024)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [Learning with Latent Structures in Natural Language Processing: A Survey](https://mlsanity.com/paper/2201.00490/) (2022)
- [Speech representation learning: Learning bidirectional encoders with single-view, multi-view, and multi-task methods](https://mlsanity.com/paper/2308.00129/) (2023)
- [Disentangling continuous and discrete linguistic signals in transformer-based sentence embeddings](https://mlsanity.com/paper/2312.11272/) (2023)

## Abstract (arXiv)

Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled sequence transduction with semi-supervised learning. The generative model can use neural networks to handle both discrete and continuous latent variables to exploit various features of data. Experiments show that our model provides not only a powerful supervised framework but also can effectively take advantage of the unlabeled data. On the SIGMORPHON morphological inflection benchmark, our model outperforms single-model state-of-art results by a large margin for the majority of languages.