Transition-Based UCCA Parser

Universal Conceptual Cognitive Annotation (UCCA) is a cross-linguistic and intuitive semantic representation scheme. It was developed in the Computational Linguistics Lab of the Computer Science Department of the Hebrew University by Omri Abend and Ari Rappoport.

This is a demo for TUPA, a transition-based UCCA parser. Given a passage, it shows a visualization of the automatically parsed UCCA graph, and XML which can be loaded using the UCCA toolkit.

TUPA was developed by Daniel Hershcovich. The source code can be found on GitHub.

TUPA is described in the following papers:

@InProceedings{hershcovich2017a,
  author    = {Hershcovich, Daniel  and  Abend, Omri  and  Rappoport, Ari},
  title     = {A Transition-Based Directed Acyclic Graph Parser for UCCA},
  booktitle = {Proc. of ACL},
  year      = {2017},
  pages     = {1127--1138},
  url       = {http://aclweb.org/anthology/P17-1104}
}

@InProceedings{hershcovich2018multitask,
  author    = {Hershcovich, Daniel  and  Abend, Omri  and  Rappoport, Ari},
  title     = {Multitask Parsing Across Semantic Representations},
  booktitle = {Proc. of ACL},
  year      = {2018},
  pages     = "373--385",
  url       = {http://aclweb.org/anthology/P18-1035}
}

Input text:

Legend
P	process
S	state
A	participant
L	linker
H	linked scene
C	center
E	elaborator
D	adverbial
R	relator
N	connector
U	punctuation
F	function
G	ground