TUPA at MRP 2019: A Multi-Task Baseline System
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- OA-TUPA
Forlagets udgivne version, 362 KB, PDF-dokument
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
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 CoNLL |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2020 |
Sider | 28-39 |
Status | Udgivet - 2020 |
Begivenhed | 2019 Conference on Natural Language Learning, CoNLL - Hong Kong, Kina Varighed: 1 nov. 2019 → 1 nov. 2019 |
Konference
Konference | 2019 Conference on Natural Language Learning, CoNLL |
---|---|
Land | Kina |
By | Hong Kong |
Periode | 01/11/2019 → 01/11/2019 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 239516689