Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
arXiv:2107.02416
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.
arXiv commentSecond Place in IWPT 2021 shared task, 7 pages
References in corpus (6)
- Distributed Representations of Words and Phrases and their Compositionality
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- CamemBERT: a Tasty French Language Model
- Multilingual is not enough: BERT for Finnish
- Playing with Words at the National Library of Sweden -- Making a Swedish BERT
- Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training