Command Palette
Search for a command to run...
{Daniel Hershcovich Ofir Arviv}
Abstract
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.
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| ucca-parsing-on-conll-2019 | Transition-based (+BERT + MTL) | Full MRP F1: 64.1 Full UCCA F1: 35.6 LPP MRP F1: 73.1 LPP UCCA F1: 50.3 |
| ucca-parsing-on-conll-2019 | Transition-based (+BERT) | Full MRP F1: 77.7 Full UCCA F1: 57.4 LPP MRP F1: 82.2 LPP UCCA F1: 65.9 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.