ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Unsupervised learning of edit parameters for matching name variants

Dan Gillick, Dilek Hakkani-Tür, Michael Levit

Since named entities are often written in different ways, question answering (QA) and other language processing tasks stand to benefit from entity matching. We address the problem of finding equivalent person names in unstructured text. Our approach is a generalization of spelling correction: We compare to candidate matches by applying a set of edits to an input name. We introduce a novel unsupervised method for learning spelling edit probabilities which improves overall F-Measure on our own name-matching task by 12%. Relevance is demonstrated by application to the GALE Distillation task.


doi: 10.21437/Interspeech.2008-77

Cite as: Gillick, D., Hakkani-Tür, D., Levit, M. (2008) Unsupervised learning of edit parameters for matching name variants. Proc. Interspeech 2008, 467-470, doi: 10.21437/Interspeech.2008-77

@inproceedings{gillick08_interspeech,
  author={Dan Gillick and Dilek Hakkani-Tür and Michael Levit},
  title={{Unsupervised learning of edit parameters for matching name variants}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={467--470},
  doi={10.21437/Interspeech.2008-77}
}