HUJI-KU at MRP 2020: Two Transition-based Neural Parsers
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- OA-HUJI-KU at MRP 2020
Final published version, 2.2 MB, PDF document
This paper describes the HUJI-KU system submission to the shared task on CrossFramework Meaning Representation Parsing (MRP) at the 2020 Conference for Computational Language Learning (CoNLL), employing TUPA and the HIT-SCIR parser, which were, respectively, the baseline system and winning system in the 2019 MRP shared task. Both are transition-based parsers using BERT contextualized embeddings. We generalized TUPA to support the newly-added MRP frameworks and languages, and experimented with multitask learning with the HIT-SCIR parser. We reached 4th place in both the crossframework and cross-lingual tracks.
Original language | English |
---|---|
Title of host publication | Proceedings of the CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing |
Publisher | Association for Computational Linguistics |
Publication date | 2020 |
Pages | 73-82 |
DOIs | |
Publication status | Published - 2020 |
Event | CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing, - Onlinr Duration: 19 Nov 2020 → 20 Nov 2020 |
Conference
Conference | CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing, |
---|---|
Location | Onlinr |
Periode | 19/11/2020 → 20/11/2020 |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
No data available
ID: 254670439