Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings

07/06/2021
by   Xinyu Wang, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/09/2018

Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation

This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 s...
research
06/02/2020

Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data

This paper presents the system used in our submission to the IWPT 2020 S...
research
10/10/2020

Automated Concatenation of Embeddings for Structured Prediction

Pretrained contextualized embeddings are powerful word representations f...
research
10/23/2020

Graph-Based Universal Dependency Parsing in the Age of the Transformer: What Works, and What Doesn't

Current state-of-the-art graph-based dependency parsers differ on variou...
research
05/25/2020

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

We present Køpsala, the Copenhagen-Uppsala system for the Enhanced Unive...
research
09/06/2023

The Microservice Dependency Matrix

Microservices have been recognized for over a decade. They reshaped syst...
research
05/22/2023

Discovering Universal Geometry in Embeddings with ICA

This study employs Independent Component Analysis (ICA) to uncover unive...

Please sign up or login with your details

Forgot password? Click here to reset