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.
Investigating a Generic Paraphrase-Based Approach for Relation Extraction
Romano, Lorenza;Kouylekov, Milen Ognianov;Szpektor, Idan;Dagan, Ido Kalman;Lavelli, Alberto
2006-01-01
Abstract
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.