Getting More Out Of Syntax with PropS

  title={Getting More Out Of Syntax with PropS},
  author={Gabriel Stanovsky and Jessica Ficler and Ido Dagan and Yoav Goldberg},
Semantic NLP applications often rely on dependency trees to recognize major elements of the proposition structure of sentences. Yet, while much semantic structure is indeed expressed by syntax, many phenomena are not easily read out of dependency trees, often leading to further ad-hoc heuristic postprocessing or to information loss. To directly address the needs of semantic applications, we present PROPS – an output representation designed to explicitly and uniformly express much of the… CONTINUE READING
Highly Cited
This paper has 25 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 4 times over the past 90 days. VIEW TWEETS

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
17 Extracted Citations
31 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 31 references

Bracketing guidelines for treebank ii style penn treebank project

  • Ann Bies, Mark Ferguson, +5 authors Britta Schasberger.
  • University of Pennsylvania, 97:100.
  • 1995
Highly Influential
4 Excerpts

Introduction to the conll-2005 shared task: Semantic role labeling

  • Xavier Carreras, Lluı́s Màrquez
  • In Proceedings of CONLL,
  • 2005
Highly Influential
8 Excerpts

Propbank: the next level of treebank

  • Paul Kingsbury, Martha Palmer.
  • Proceedings of Treebanks and lexical Theories…
  • 2003
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…