# AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network

arXiv: https://arxiv.org/abs/2009.08229 · HTML: https://mlsanity.com/paper/2009.08229/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints](https://mlsanity.com/paper/2309.15458/) (2023)
- [Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms](https://mlsanity.com/paper/2506.00732/) (2025)
- [Diffusion-MF: Approximate Structured Diffusion for Sequence Labelling](https://mlsanity.com/paper/2606.18856/) (2026)

## Abstract (arXiv)

The linear-chain Conditional Random Field (CRF) model is one of the most widely-used neural sequence labeling approaches. Exact probabilistic inference algorithms such as the forward-backward and Viterbi algorithms are typically applied in training and prediction stages of the CRF model. However, these algorithms require sequential computation that makes parallelization impossible. In this paper, we propose to employ a parallelizable approximate variational inference algorithm for the CRF model. Based on this algorithm, we design an approximate inference network that can be connected with the encoder of the neural CRF model to form an end-to-end network, which is amenable to parallelization for faster training and prediction. The empirical results show that our proposed approaches achieve a 12.7-fold improvement in decoding speed with long sentences and a competitive accuracy compared with the traditional CRF approach.