Intermediary Semantic Representation through Proposition Structures

Gabriel Stanovsky, Jessica Ficler, Ido Dagan, Yoav Goldberg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We propose an intermediary-level semanticrepresentation, providing a higher levelof abstraction than syntactic parse trees,while not committing to decisions in casessuch as quantification, grounding or verbspecificroles assignments. The proposalis centered around the proposition structureof the text, and includes also implicitpropositions which can be inferredfrom the syntax but are not transparent inparse trees, such as copular relations introducedby appositive constructions. Otherbenefits over dependency-trees are explicitmarking of logical relations betweenpropositions, explicit marking of multiwordpredicate such as light-verbs, and aconsistent representation for syntacticallydifferentbut semantically-similar structures.The representation is meant toserve as a useful input layer for semanticorientedapplications, as well as to providea better starting point for further levels ofsemantic analysis such as semantic-rolelabelingand semantic-parsing.
Original languageAmerican English
Title of host publicationProceedings of the First AHA!-Workshop on Information Discovery in Text
Number of pages5
StatePublished - 1 Jan 2014


Dive into the research topics of 'Intermediary Semantic Representation through Proposition Structures'. Together they form a unique fingerprint.

Cite this