The ADAPT Enhanced Dependency Parser at the IWPT 2020 Shared Task

Abstract

We describe the ADAPT system for the 2020 IWPT Shared Task on parsing enhanced Universal Dependencies in 17 languages. We implement a pipeline approach using UDPipe and UDPipe-future to provide initial levels of annotation. The enhanced dependency graph is either produced by a graph-based semantic dependency parser or is built from the basic tree using a small set of heuristics. Our results show that, for the majority of languages, a semantic dependency parser can be successfully applied to the task of parsing enhanced dependencies. Unfortunately, we did not ensure a connected graph as part of our pipeline approach and our competition submission relied on a last-minute fix to pass the validation script which harmed our official evaluation scores significantly. Our submission ranked eighth in the official evaluation with a macro-averaged coarse ELAS F1 of 67.23 and a treebank average of 67.49. We later implemented our own graph-connecting fix which resulted in a score of 79.53 (language average) or 79.76 (treebank average), which would have placed fourth in the competition evaluation.

Submitted to the 2020 IWPT shared task on parsing Enhanced Universal Dependencies

References in corpus (7)

• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• CamemBERT: a Tasty French Language Model
• Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language
• BERTje: A Dutch BERT Model
• Multilingual is not enough: BERT for Finnish
• Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation
• Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing

Cited by in corpus (2)

• TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning
• Revisiting Tri-training of Dependency Parsers