MRP 2019: Cross-Framework Meaning Representation Parsing

Oepen, Stephan; Abend, Omri; Hajič, Jan; Hershcovich, Daniel; Kuhlmann, Marco; O'Gorman, Tim; Xue, Nianwen; Chun, Jayeol; Straka, Milan; Urešová, Zdeňka

doi:10.18653/v1/k19-2001

Cited by 53 publications

(66 citation statements)

References 63 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The CoNLL 2019 Shared Task (Oepen et al, 2019) combines five frameworks for graph-based meaning representation: DM, PSD, EDS, UCCA and AMR. For the task, TUPA was extended to support the MRP format and frameworks, and is used as a baseline system, both as a single-task system trained separately on each framework, and as a multi-task system trained on all of them.…”

Section: Introductionmentioning

confidence: 99%

TUPA at MRP 2019: A Multi-Task Baseline System

Hershcovich¹,

Arviv²

2019

Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Lea

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

TUPA at MRP 2019: A Multi-Task Baseline System

Hershcovich¹,

Arviv²

2019

Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Lea

Self Cite

View full text Add to dashboard Cite

show abstract

“…For different frameworks, organizers design different evaluation criteria and provide standard evaluation scripts. Details about the five semantic formalisms and evaluation criteria are given in the MRP shared task homepage 1 and the overview paper (Oepen et al, 2019). In the following, we give a brief introduction of each framework and followed by our corresponding approaches.…”

Section: Introductionmentioning

confidence: 99%

SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT

Zhang¹,

Jiang²,

Xia³

et al. 2019

Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Lea

View full text Add to dashboard Cite

In this paper, we describe our participating systems in the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). The task includes five frameworks for graph-based meaning representations, i.e., DM, PSD, EDS, UCCA, and AMR. One common characteristic of our systems is that we employ graph-based methods instead of transition-based methods when predicting edges between nodes. For SDP, we jointly perform edge prediction, frame tagging, and POS tagging via multi-task learning (MTL). For UCCA, we also jointly model a constituent tree parsing and a remote edge recovery task. For both EDS and AMR, we produce nodes first and edges second in a pipeline fashion. External resources like BERT are found helpful for all frameworks except AMR. Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.

show abstract

“…The CoNLL 2019 Shared Task (Oepen et al, 2019) combines formally and linguistically different meaning representation in graph form on a uniform training and evaluation setup for the first time. This task includes five MRP frameworks: DM, PSD, EDS, UCCA, and AMR.…”

Section: Introductionmentioning

confidence: 99%

SJTU at MRP 2019: A Transition-Based Multi-Task Parser for Cross-Framework Meaning Representation Parsing

Bai¹,

Zhao²

2019

Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Lea

View full text Add to dashboard Cite

This paper describes the system of our team SJTU for our participation in the CoNLL 2019 Shared Task: Cross-Framework Meaning Representation Parsing. The goal of the task is to advance data-driven parsing into graphstructured representations of sentence meaning. This task includes five meaning representation frameworks: DM, PSD, EDS, UCCA, and AMR. These frameworks have different properties and structures. To tackle all the frameworks in one model, it is needed to find out the commonality of them. In our work, we define a set of the transition actions to oncefor-all tackle all the frameworks and train a transition-based model to parse the meaning representation. The adopted multi-task model also can allow learning for one framework to benefit the others. In the final official evaluation of the shared task, our system achieves 42% F 1 unified MRP metric score.

show abstract

MRP 2019: Cross-Framework Meaning Representation Parsing

Cited by 53 publications

References 63 publications

TUPA at MRP 2019: A Multi-Task Baseline System

TUPA at MRP 2019: A Multi-Task Baseline System

SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT

SJTU at MRP 2019: A Transition-Based Multi-Task Parser for Cross-Framework Meaning Representation Parsing

Contact Info

Product

Resources

About