Multi-Layer Pseudo-Siamese Biaffine Model for Dependency Parsing
Biaffine method is a strong and efficient method for graph-based dependency parsing. However, previous work only used the biaffine method at the end of the dependency parser as a scorer, and its application in multi-layer form is ignored. In this paper, we propose a multi-layer pseudo-Siamese biaffine model for neural dependency parsing. In this model, we modify the biaffine method so that it can be utilized in multi-layer form, and use pseudo-Siamese biaffine module to construct arc weight matrix for final prediction. In our proposed multi-layer architecture, the biaffine method plays important roles in both scorer and attention mechanism at the same time in each layer. We evaluate our model on PTB, CTB, and UD. The model achieves state-of-the-art results on these datasets. Further experiments show the benefits of introducing multi-layer form and pseudo-Siamese module into the biaffine method with low efficiency loss.
Code (1)
Tasks
ARCDependency ParsingFormSimilar Papers 제목 키워드 기반
Multi-layer Biaffine Model for Neural Dependency Parsing
The biaffine model is a strong and efficient model for graph-based dependency parsing. However, previous work only used the biaffine method in single-layer form. In this paper, we propose a multi-layer biaffine model for…
Dependency ParsingFormDependency Parsing is More Parameter-Efficient with Normalization
Dependency parsing is the task of inferring natural language structure, often approached by modeling word interactions via attention through biaffine scoring. This mechanism works like self-attention in Transformers, whe…
Dependency ParsingSentenceJBNU at MRP 2019: Multi-level Biaffine Attention for Semantic Dependency Parsing
This paper describes Jeonbuk National University (JBNU){'}s system for the 2019 shared task on Cross-Framework Meaning Representation Parsing (MRP 2019) at the Conference on Computational Natural Language Learning. Of th…
DecoderDependency ParsingSemantic Dependency ParsingSentenceEnd-to-End Argument Mining as Biaffine Dependency Parsing
Non-neural approaches to argument mining (AM) are often pipelined and require heavy feature-engineering. In this paper, we propose a neural end-to-end approach to AM which is based on dependency parsing, in contrast to t…
Argument MiningDependency ParsingFeature EngineeringRelation+1Efficient Second-Order TreeCRF for Neural Dependency Parsing
In the deep learning (DL) era, parsing models are extremely simplified with little hurt on performance, thanks to the remarkable capability of multi-layer BiLSTMs in context representation. As the most popular graph-base…
ARCChinese Dependency ParsingDependency Parsing