Dependency Parsing with the Structuralized Prompt Template

TL;DR

This paper introduces a novel dependency parsing approach using a structured prompt template with a text-to-text encoder model, achieving high performance and adaptability across languages without additional layers.

Contribution

It presents a new dependency parsing method that leverages a structured prompt template and a text-to-text encoder, eliminating the need for traditional embedding and layer-based prediction.

Findings

Achieves superior performance compared to traditional models.

Highly adaptable across different languages and training environments.

Simplifies dependency parsing by using only a pre-trained encoder.

Abstract

Dependency parsing is a fundamental task in natural language processing (NLP), aiming to identify syntactic dependencies and construct a syntactic tree for a given sentence. Traditional dependency parsing models typically construct embeddings and utilize additional layers for prediction. We propose a novel dependency parsing method that relies solely on an encoder model with a text-to-text training approach. To facilitate this, we introduce a structured prompt template that effectively captures the structural information of dependency trees. Our experimental results demonstrate that the proposed method achieves outstanding performance compared to traditional models, despite relying solely on a pre-trained model. Furthermore, this method is highly adaptable to various pre-trained models across different target languages and training environments, allowing easy integration of task-specific features.