论文标题
MRP 〜2020年的Huji-Ku：两个基于过渡的神经解析器
HUJI-KU at MRP~2020: Two Transition-based Neural Parsers
论文作者
论文摘要
本文介绍了在2020年计算语言学习会议上（CONLL），使用TUPA和HIT-SCIR PARSER的跨框架含义表示解析（MRP）的共享任务的Huji-Ku系统提交，分别是2019年MRP共享任务。两者都是使用BERT上下文化嵌入的基于过渡的解析器。我们将TUPA概括为支持新添加的MRP框架和语言，并通过Hit-Scir Parser尝试了多任务学习。我们在跨框架和跨语言轨道中排名第四。
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.
