# Neural Probabilistic Model for Non-projective MST Parsing

arXiv: https://arxiv.org/abs/1701.00874 · HTML: https://mlsanity.com/paper/1701.00874/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2017.

## Built on by (most cited first, 6 of 6)

- [Dependency Parsing with Bottom-up Hierarchical Pointer Networks](https://mlsanity.com/paper/2105.09611/) (2021)
- [On Finding the K-best Non-projective Dependency Trees](https://mlsanity.com/paper/2106.00780/) (2021)
- [An In-depth Study on Internal Structure of Chinese Words](https://mlsanity.com/paper/2106.00334/) (2021)
- [Efficient Sampling of Dependency Structures](https://mlsanity.com/paper/2109.06521/) (2021)
- [Early stopping by correlating online indicators in neural networks](https://mlsanity.com/paper/2402.02513/) (2024)
- [Absolute convergence and error thresholds in non-active adaptive sampling](https://mlsanity.com/paper/2402.02522/) (2024)

## Abstract (arXiv)

In this paper, we propose a probabilistic parsing model, which defines a proper conditional probability distribution over non-projective dependency trees for a given sentence, using neural representations as inputs. The neural network architecture is based on bi-directional LSTM-CNNs which benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM and CNN. On top of the neural network, we introduce a probabilistic structured layer, defining a conditional log-linear model over non-projective trees. We evaluate our model on 17 different datasets, across 14 different languages. By exploiting Kirchhoff's Matrix-Tree Theorem (Tutte, 1984), the partition functions and marginals can be computed efficiently, leading to a straight-forward end-to-end model training procedure via back-propagation. Our parser achieves state-of-the-art parsing performance on nine datasets.