HUJI-KU at MRP~2020: Two Transition-based Neural Parsers

12 Oct 2020 Ofir Arviv Ruixiang Cui Daniel Hershcovich

This paper describes the HUJI-KU system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2020 Conference for Computational Language Learning (CoNLL), employing TUPA and the HIT-SCIR parser, which were, respectively, the baseline system and winning system in the 2019 MRP shared task. Both are transition-based parsers using BERT contextualized embeddings... (read more)

PDF Abstract
No code implementations yet. Submit your code now
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semantic Parsing AMR (chinese, MRP 2020) HUJI-KU F1 45 # 2
Semantic Parsing AMR (english, MRP 2020) HUJI-KU F1 52 # 2
Semantic Parsing DRG (english, MRP 2020) HUJI-KU F1 63 # 2
Semantic Parsing DRG (german, MRP 2020) HUJI-KU F1 62 # 2
Semantic Parsing EDS (english, MRP 2020) HUJI-KU F1 80 # 2
Semantic Parsing PTG (czech, MRP 2020) HUJI-KU F1 58 # 2
Semantic Parsing PTG (english, MRP 2020) HUJI-KU F1 54 # 2
Semantic Parsing UCCA (english, MRP 2020) HUJI-KU F1 73 # 2
Semantic Parsing UCCA (german, MRP 2020) HUJI-KU F1 75 # 2

Methods used in the Paper