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.
翻译:本文件介绍在2020年计算语言学习会议(CONNLL)上,HUJI-KU系统就跨框架代表分析(MRP)共同任务提交的文件,其中分别使用TUPA和HIT-SCIR分析员,这是2019年MRP共同任务的基线系统和获胜系统,两者都是使用BERT背景嵌入的基于过渡的授精器。我们普及了TUPA,以支持新增加的MRP框架和语言,并与HIT-SCIR分析员进行了多任务学习试验。我们在跨框架和跨语言轨道上都达到了第四位。