MRP 2020: The Second Shared Task on Cross-Framework and Cross-Lingual Meaning Representation Parsing

Abstract

The 2020 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks and languages. Extending a similar setup from the previous year, five distinct approaches to the representation of sentence meaning in the form of directed graphs were represented in the English training and evaluation data for the task, packaged in a uniform graph abstraction and serialization; for four of these representation frameworks, additional training and evaluation data was provided for one additional language per framework. The task received submissions from eight teams, of which two do not participate in the official ranking because they arrived after the closing deadline or made use of additional training data. All technical information regarding the task, including system submissions, official results, and links to supporting resources and software are available from the task web site at:

SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation

“…In this sense, we continue the recent cross-framework trend formally started by the shared task of Oepen et al (2019), exploring the possibility of using translation-based approaches for framework-independent parsing, as opposed to the transition-based parsers proposed in that seminal work. Our findings are in line with the recent results reported by Oepen et al (2020) and, in particular, by Ozaki et al (2020) (d) UCCA Linearization Figure 1: AMR and UCCA graphs, along with their linearizations, for the sentence "After graduation, John moved to Paris". To ease readability, linearizations are shown with newlines and indentation; however, when fed to the neural model, they are in a single-line single-space format.…”

“…First of all, we note the result of Cross st ; while its performance is far below the score Che et al (2019) achieve, it still outperforms the original proposed baseline by more than 10 points. Furthermore, to the best of our knowledge, apart from the recent works proposed in the latest shared task of Oepen et al (2020), this is the first reported result of translation-based approaches on UCCA parsing.…”

“…As a result of this heterogeneous landscape, often referred to as framework-specific balkanization (Oepen et al, 2020), graph-based semantic parsing has seen a proliferation of framework-specific solutions. However, approaches capable of competitively scaling across formalisms represent a natural desideratum, and recent works have started to explore this direction, examining the usage of multi-task learning in different architectures (Hershcovich et al, 2018;Oepen et al, 2019), or casting different formalisms under a unified framework where models can be trained to perform graph transduction (Zhang et al, 2019b).…”

From Raw Text to Enhanced Universal Dependencies: The Parsing Shared Task at IWPT 2021

“…Moreover, most state-of-the-art work in dependency parsing uses a graph-based approach, where the assumption that the output must form a tree is only used in the final step from predicted links to final output. And finally, work on deep-syntax and semantic parsing has shown that accurate mapping of strings into rich graph representations is possible (Oepen et al, 2014(Oepen et al, , 2015(Oepen et al, , 2019(Oepen et al, , 2020 and could even lead to state-of-the-art performance for downstream applications as shown by the results of the Extrinsic Parsing Evaluation shared task (Oepen et al, 2017).…”

Great Service! Fine-grained Parsing of Implicit Arguments

“…Universal Conceptual Cognitive Annotation (UCCA; Abend and Rappoport, 2013), a typologically-motivated meaning representation framework, has been targeted by several parsing shared tasks (Hershcovich et al, 2019b;Oepen et al, 2019Oepen et al, , 2020. It uses directed acyclic graphs (DAG) anchored in surface tokens, where labelled edges represent semantic relations.…”