HUJI-KU at MRP~2020: Two Transition-based Neural Parsers
2020-10-12Unverified0· sign in to hype
Ofir Arviv, Ruixiang Cui, Daniel Hershcovich
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
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. We generalized TUPA to support the newly-added MRP frameworks and languages, and experimented with multitask learning with the HIT-SCIR parser. We reached 4th place in both the cross-framework and cross-lingual tracks.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| AMR (chinese, MRP 2020) | HUJI-KU | F1 | 45 | — | Unverified |
| AMR (english, MRP 2020) | HUJI-KU | F1 | 52 | — | Unverified |
| DRG (english, MRP 2020) | HUJI-KU | F1 | 63 | — | Unverified |
| DRG (german, MRP 2020) | HUJI-KU | F1 | 62 | — | Unverified |
| EDS (english, MRP 2020) | HUJI-KU | F1 | 80 | — | Unverified |
| PTG (czech, MRP 2020) | HUJI-KU | F1 | 58 | — | Unverified |
| PTG (english, MRP 2020) | HUJI-KU | F1 | 54 | — | Unverified |
| UCCA (english, MRP 2020) | HUJI-KU | F1 | 73 | — | Unverified |
| UCCA (german, MRP 2020) | HUJI-KU | F1 | 75 | — | Unverified |