TUPA at MRP 2019: A Multi-Task Baseline System
This paper describes the TUPA system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Because it was prepared by one of the task co-organizers, TUPA provides a baseline point of comparison and is not considered in the official ranking of participating systems. While originally developed for UCCA only, TUPA has been generalized to support all MRP frameworks included in the task, and trained using multi-task learning to parse them all with a shared model. It is a transition-based parser with a BiLSTM encoder, augmented with BERT contextualized embeddings.
PDF AbstractDatasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
UCCA Parsing | CoNLL 2019 | Transition-based (+BERT + MTL) | Full UCCA F1 | 35.6 | # 3 | |
Full MRP F1 | 64.1 | # 3 | ||||
LPP UCCA F1 | 50.3 | # 3 | ||||
LPP MRP F1 | 73.1 | # 3 | ||||
UCCA Parsing | CoNLL 2019 | Transition-based (+BERT) | Full UCCA F1 | 57.4 | # 2 | |
Full MRP F1 | 77.7 | # 2 | ||||
LPP UCCA F1 | 65.9 | # 1 | ||||
LPP MRP F1 | 82.2 | # 2 |