TUPA at MRP 2019: A Multi-Task Baseline System

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Documents

  • OA-TUPA

    Final published version, 362 KB, PDF document

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
Original languageEnglish
Title of host publicationProceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 CoNLL
PublisherAssociation for Computational Linguistics
Publication date2020
Pages28-39
Publication statusPublished - 2020
Event2019 Conference on Natural Language Learning, CoNLL - Hong Kong, China
Duration: 1 Nov 20191 Nov 2019

Conference

Conference2019 Conference on Natural Language Learning, CoNLL
LandChina
ByHong Kong
Periode01/11/201901/11/2019

Number of downloads are based on statistics from Google Scholar and www.ku.dk


No data available

ID: 239516689