paper-with-me

Papers

Multi-Layer Pseudo-Siamese Biaffine Model for Dependency Parsing

2022-10-01 · COLING 2022 10 · Ziyao Xu, Houfeng Wang, Bingdong Wang

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.

📄 PDF Abstract BibTeX

Code (1)

xzy-xzy/mlpsb-parser 공식 구현 pytorch

Tasks

ARCDependency ParsingForm

Similar Papers 제목 키워드 기반

Multi-layer Biaffine Model for Neural Dependency Parsing

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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 ParsingForm

Dependency Parsing is More Parameter-Efficient with Normalization

2025-05-26 · Paolo Gajo, Domenic Rosati, Hassan Sajjad, Alberto Barrón-Cedeño

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 ParsingSentence

JBNU at MRP 2019: Multi-level Biaffine Attention for Semantic Dependency Parsing

2019-11-01 · CONLL 2019 11 · Seung-Hoon Na, Jinwoon Min, Kwanghyeon Park, Jong-Hun Shin 외

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 ParsingSentence

End-to-End Argument Mining as Biaffine Dependency Parsing

2021-04-01 · EACL 2021 2 · Yuxiao Ye, Simone Teufel

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+1

Efficient Second-Order TreeCRF for Neural Dependency Parsing

2020-05-03 · ACL 2020 6 · Yu Zhang, Zhenghua Li, Min Zhang

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