Cardinal Virtues: Extracting Relation Cardinalities from Text

@inproceedings{Mirza2017CardinalVE,
  title={Cardinal Virtues: Extracting Relation Cardinalities from Text},
  author={Paramita Mirza and Simon Razniewski and Fariz Darari and Gerhard Weikum},
  booktitle={ACL},
  year={2017}
}
Information extraction (IE) from text has largely focused on relations between individual entities, such as who has won which award. However, some facts are never fully mentioned, and no IE method has perfect recall. Thus, it is beneficial to also tap contents about the cardinalities of these relations, for example, how many awards someone has won. We introduce this novel problem of extracting cardinalities and discusses the specific challenges that set it apart from standard IE. We present a… CONTINUE READING
7
Twitter Mentions

Tables, Results, and Topics from this paper.

Key Quantitative Results

  • It is shown that with 30 manually crafted patterns and simple filters it is possible to extract 86,227 children-cardinality-assertions with a precision of 94.3%.

Citations

Publications citing this paper.
SHOWING 1-10 OF 12 CITATIONS

References

Publications referenced by this paper.