Neural Probabilistic Model for Non-projective MST Parsing
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.
Code (0)
등록된 구현이 없습니다.
Tasks
modelSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Probabilistic Models for High-Order Projective Dependency Parsing
This paper presents generalized probabilistic models for high-order projective dependency parsing and an algorithmic framework for learning these statistical models involving dependency trees. Partition functions and mar…
Dependency Parsingparameter estimationVocal Bursts Intensity PredictionGlobal Transition-based Non-projective Dependency Parsing
Shi, Huang, and Lee (2017) obtained state-of-the-art results for English and Chinese dependency parsing by combining dynamic-programming implementations of transition-based dependency parsers with a minimal set of bidire…
Chinese Dependency ParsingDependency ParsingSequential Graph Dependency Parser
We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, tr…
Dependency ParsingHeaded-Span-Based Projective Dependency Parsing
We propose a new method for projective dependency parsing based on headed spans. In a projective dependency tree, the largest subtree rooted at each word covers a contiguous sequence (i.e., a span) in the surface order. …
Constituency ParsingDependency ParsingCalculating the optimal step of arc-eager parsing for non-projective trees
It is shown that the optimal next step of an arc-eager parser relative to a non-projective dependency structure can be calculated in cubic time, solving an open problem in parsing theory. Applications are in training of …
ARC