TUPA at MRP 2019: A Multi-Task Baseline System
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
TUPA at MRP 2019 : A Multi-Task Baseline System. / Hershcovich, Daniel; Arviv, Ofir .
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 CoNLL. Association for Computational Linguistics, 2020. p. 28-39.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - TUPA at MRP 2019
T2 - 2019 Conference on Natural Language Learning, CoNLL
AU - Hershcovich, Daniel
AU - Arviv, Ofir
PY - 2020
Y1 - 2020
N2 - 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). 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
AB - 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). 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
M3 - Article in proceedings
SP - 28
EP - 39
BT - Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 CoNLL
PB - Association for Computational Linguistics
Y2 - 1 November 2019 through 1 November 2019
ER -
ID: 239516689