Neural Probabilistic Model for Non-projective MST Parsing
This work addresses dependency parsing for multiple languages, offering a novel method that improves accuracy in a specific NLP task.
The paper tackles the problem of non-projective dependency parsing by proposing a neural probabilistic model that defines a conditional distribution over trees, achieving state-of-the-art performance on nine out of 17 datasets across 14 languages.
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.