Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding

2020/05/25 by Daniel Hershcovich, Miryam de Lhoneux, Hershcovich, Daniel +7
Computer Science · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.2005.12094

IWPT shared task 2020

openalex publication_date 2020/05/25 · arxiv created 2020/06/02 · arxiv updated 2020/06/03 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28

Abstract

We present Køpsala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020. Our system is a pipeline consisting of off-the-shelf models for everything but enhanced graph parsing, and for the latter, a transition-based graph parser adapted from Che et al. (2019). We train a single enhanced parser model per language, using gold sentence splitting and tokenization for training, and rely only on tokenized surface forms and multilingual BERT for encoding. While a bug introduced just before submission resulted in a severe drop in precision, its post-submission fix would bring us to 4th place in the official ranking, according to average ELAS. Our parser demonstrates that a unified pipeline is effective for both Meaning Representation Parsing and Enhanced Universal Dependencies.

Related

• UniParse: A universal graph-based parsing toolkit
• The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task
• Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
• Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data
• Applying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really Necessary