HUJI-KU at MRP~2020: Two Transition-based Neural Parsers
This is an incremental improvement for computational linguistics researchers working on parsing tasks.
The paper tackled the problem of meaning representation parsing across frameworks and languages by generalizing an existing parser and experimenting with multitask learning, achieving 4th place in cross-framework and cross-lingual tracks.
This paper describes the HUJI-KU system submission to the shared task on Cross-Framework 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 cross-framework and cross-lingual tracks.