UCD-PN: Selecting general paraphrases using conditional probability

Authors:
Paul Nulty;Fintan Costello
Affiliations:
University College Dublin, Dublin, Ireland;University College Dublin, Dublin, Ireland
Venue:
SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
Year:
2010

Citing 1
Cited 2

SemEval-2010 task 9: The interpretation of noun compounds using paraphrasing verbs and prepositions

SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation

"Nut case: what does it mean?": understanding semantic relationship between nouns in noun compounds through paraphrasing and ranking the paraphrases

Proceedings of the 1st international workshop on Search and mining entity-relationship data
Probabilistic models of similarity in syntactic context

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a system which ranks human-provided paraphrases of noun compounds, where the frequency with which a given paraphrase was provided by human volunteers is the gold standard for ranking. Our system assigns a score to a paraphrase of a given compound according to the number of times it has co-occurred with other paraphrases in the rest of the dataset. We use these co-occurrence statistics to compute conditional probabilities to estimate a sub-typing or Is-A relation between paraphrases. This method clusters together paraphrases which have similar meanings and also favours frequent, general paraphrases rather than infrequent paraphrases with more specific meanings.