Using Commonsense Knowledge to Disambiguate Prepositional Phrase Modifiers

Abstract

This paper describes a method using commonsense knowledge for discarding spurious syntactic ambiguities introduced by post-verbal prepositional phrase attachment during parsing. A com-pletely naive parser will generate three parses for sentences of the form NP-V-Det-N-PP. The prepositions alone are insufficiently pre-cise in meaning to guide selection among competing parses. The method is imbedded in the Kind Types System (KT) which employs commonsense knowledge of concepts, including prototype and in-herent features (generic information) and ontological classifica-tions. The generic information is drawn from published psycholinguistic studies on how average people typically view the world. This method is employed in preference strategies which appeal to the meaning of the preposition combined with information about the verbs and nouns associated with it drawn from the text

Cite

Text

Dahlgren and McDowell. "Using Commonsense Knowledge to Disambiguate Prepositional Phrase Modifiers." AAAI Conference on Artificial Intelligence, 1986.

Markdown

[Dahlgren and McDowell. "Using Commonsense Knowledge to Disambiguate Prepositional Phrase Modifiers." AAAI Conference on Artificial Intelligence, 1986.](https://mlanthology.org/aaai/1986/dahlgren1986aaai-using/)

BibTeX

@inproceedings{dahlgren1986aaai-using,
  title     = {{Using Commonsense Knowledge to Disambiguate Prepositional Phrase Modifiers}},
  author    = {Dahlgren, Kathleen and McDowell, Joyce P.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1986},
  pages     = {589-593},
  url       = {https://mlanthology.org/aaai/1986/dahlgren1986aaai-using/}
}