Investigating a Generic Paraphrase-Based Approach for Relation Extraction

L Romano, M Kouylekov, I Szpektor, I Dagan, A Lavelli

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Unsupervised paraphrase acquisition has been an active research field in recent years, but its effective coverage and performance have rarely been evaluated. We propose a generic paraphrase-based approach for Relation Extraction (RE), aiming at a dual goal: obtaining an applicative evaluation scheme for paraphrase acquisition and obtaining a generic and largely unsupervised configuration for RE. We analyze the potential of our approach and evaluate an implemented prototype of it using an RE dataset. Our findings reveal a high potential for unsupervised paraphrase acquisition. We also identify the need for novel robust models for matching paraphrases in texts, which should address syntactic complexity and variability
Original languageAmerican English
Title of host publicationEACL
StatePublished - 2006

Bibliographical note

Place of conference:Trento, Italy

Cite this