Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
This work addresses parsing accuracy for multilingual NLP applications, but it is incremental as it builds on existing embedding concatenation methods.
The paper tackled enhanced universal dependency parsing by using Automated Concatenation of Embeddings (ACE) to optimize word representations, resulting in a system that ranked 2nd out of 9 teams across 17 languages.
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.