Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings

TL;DR

This paper introduces a graph-based parser utilizing Automated Concatenation of Embeddings (ACE) to improve enhanced universal dependency parsing, achieving high accuracy across multiple languages.

Contribution

It presents a novel ACE technique for automatically optimizing embedding concatenations in dependency parsing models.

Findings

Achieved 2nd place in IWPT 2021 Shared Task

Improved parsing accuracy across 17 languages

Demonstrated effectiveness of embedding concatenation optimization

Abstract

This paper describes the system used in submission from SHANGHAITECH team to the IWPT 2021 Shared Task. Our system is a graph-based parser with the technique of Automated Concatenation of Embeddings (ACE). Because recent work found that better word representations can be obtained by concatenating different types of embeddings, we use ACE to automatically find the better concatenation of embeddings for the task of enhanced universal dependencies. According to official results averaged on 17 languages, our system ranks 2nd over 9 teams.