A Consolidated Open Knowledge Representation for Multiple Texts

@inproceedings{Wities2017ACO,
  title={A Consolidated Open Knowledge Representation for Multiple Texts},
  author={Rachel Wities and Vered Shwartz and Gabriel Stanovsky and Meni Adler and Ori Shapira and Shyam Upadhyay and Dan Roth and Eugenio Martinez Camara and Iryna Gurevych and Ido Dagan},
  year={2017}
}
We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open textbased manner. We do so by consolidating OIE extractions using entity and predicate coreference, while modeling information containment between coreferring elements via lexical entailment. We suggest that generating OKR structures can be a useful step in the NLP pipeline, to give semantic applications an easy… CONTINUE READING