Answer Validation is an emerging topic in Question Anszering, where open domain systems are often required to rank huge amounts of candidate answers. We present a novel approach to answer validation based on the intuition that the amount of implicit knowledge which connects an answer to a question can be quantitatively estimated by exploiting the redundancy of Web information. Experiments carried out on the TREC-10 corpus show that the approach achieves a high level of performance (i.e. 80% success rate). The simplicity and the efficiency of this approach make it suitable to be used as a module in Question Answering systems.
Is It the Right Answer? Exploiting Web Redundancy for Answer Validation
Magnini, Bernardo;Negri, Matteo;Prevete, Roberto;Tanev, Hristo
2002-01-01
Abstract
Answer Validation is an emerging topic in Question Anszering, where open domain systems are often required to rank huge amounts of candidate answers. We present a novel approach to answer validation based on the intuition that the amount of implicit knowledge which connects an answer to a question can be quantitatively estimated by exploiting the redundancy of Web information. Experiments carried out on the TREC-10 corpus show that the approach achieves a high level of performance (i.e. 80% success rate). The simplicity and the efficiency of this approach make it suitable to be used as a module in Question Answering systems.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
