# Variational Sequential Labelers for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/1906.09535 · HTML: https://mlsanity.com/paper/1906.09535/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2019.

## Built on by (most cited first, 11 of 11)

- [The Rich Get Richer: Disparate Impact of Semi-Supervised Learning](https://mlsanity.com/paper/2110.06282/) (2021)
- [Cross-SEAN: A Cross-Stitch Semi-Supervised Neural Attention Model for COVID-19 Fake News Detection](https://mlsanity.com/paper/2102.08924/) (2021)
- [Debiasing Learning for Membership Inference Attacks Against Recommender Systems](https://mlsanity.com/paper/2206.12401/) (2022)
- [Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction](https://mlsanity.com/paper/2112.09215/) (2021)
- [Span-based Named Entity Recognition by Generating and Compressing Information](https://mlsanity.com/paper/2302.05392/) (2023)
- [Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling](https://mlsanity.com/paper/2302.08659/) (2023)
- [Rank-Aware Negative Training for Semi-Supervised Text Classification](https://mlsanity.com/paper/2306.07621/) (2023)
- [Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation](https://mlsanity.com/paper/2305.15872/) (2023)
- [Challenging the Semi-Supervised VAE Framework for Text Classification](https://mlsanity.com/paper/2109.12969/) (2021)
- [RevUp: Revise and Update Information Bottleneck for Event Representation](https://mlsanity.com/paper/2205.12248/) (2022)
- [A Probabilistic Semi-Supervised Approach with Triplet Markov Chains](https://mlsanity.com/paper/2309.03707/) (2023)

## Abstract (arXiv)

We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative labeler. The generative models use latent variables to define the conditional probability of a word given its context, drawing inspiration from word prediction objectives commonly used in learning word embeddings. The labeler helps inject discriminative information into the latent space. We explore several latent variable configurations, including ones with hierarchical structure, which enables the model to account for both label-specific and word-specific information. Our models consistently outperform standard sequential baselines on 8 sequence labeling datasets, and improve further with unlabeled data.