We present the SemEval 2019 shared task on Universal Conceptual Cognitive Annotation (UCCA) parsing in English, German and French, and discuss the participating systems and results. UCCA is a cross-linguistically applicable framework for semantic representation, which builds on extensive typological work and supports rapid annotation. UCCA poses a challenge for existing parsing techniques, as it exhibits reentrancy (resulting in DAG structures), discontinuous structures and non-terminal nodes corresponding to complex semantic units. The shared task has yielded improvements over the state-of-the-art baseline in all languages and settings. Full results can be found in the task’s website https://competitions.codalab.org/competitions/19160.
@inproceedings{DBLP:conf/semeval/HershcovichACSR19,
author = {Daniel Hershcovich and
Zohar Aizenbud and
Leshem Choshen and
Elior Sulem and
Ari Rappoport and
Omri Abend},
editor = {Jonathan May and
Ekaterina Shutova and
Aur{\'{e}}lie Herbelot and
Xiaodan Zhu and
Marianna Apidianaki and
Saif M. Mohammad},
title = {SemEval-2019 Task 1: Cross-lingual Semantic Parsing with {UCCA}},
booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation,
SemEval@NAACL-HLT 2019, Minneapolis, MN, USA, June 6-7, 2019},
pages = {1--10},
publisher = {Association for Computational Linguistics},
year = {2019},
url = {https://doi.org/10.18653/v1/s19-2001},
doi = {10.18653/V1/S19-2001},
timestamp = {Thu, 25 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/semeval/HershcovichACSR19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
See the full reference list in the paper.