Exploring Sentence Retrieval - Couverture souple

Murdock, Vanessa

Couverture souple

ISBN 10 : 3836437651 ISBN 13 : 9783836437653

Editeur : VDM Verlag Dr. Mueller E.K., 2008

Synopsis

Sentence Retrieval is the task of retrieving a relevant sentence in response to a query, a question, or a reference sentence. In this work we begin by demonstrating that because sentences are much smaller than documents, the performance of typical document retrieval systems on the retrieval of sentences is significantly worse. We propose several solutions to the problem of sentence retrieval, based on statistical translation models, and investigate these solutions the application areas of sentence retrieval for question answering, novelty detection, and information provenance. Statistical trans-lation models are appropriate for tasks where the sentence to be retrieved benefits from the addition of related terms and synonyms. The context of a sentence affects its meaning, and smoothing from the local context of the sentence improves retrieval. A brief investigation of conditional models for sentence retrieval suggests conditional models outperform language modeling approaches, for some tasks. This book is addressed to students and professionals working on language technology systems that are dependent on sentence or passage retrieval.

A propos du livre

Présentation de l'éditeur

Revision with unchanged content. Sentence Retrieval is the task of retrieving a relevant sentence in response to a query, a question, or a reference sentence. In this work we begin by demonstrating that because sentences are much smaller than documents, the performance of typical document retrieval systems on the retrieval of sentences is significantly worse. We propose several solutions to the problem of sentence retrieval, based on statistical translation models, and investigate these solutions the application areas of sentence retrieval for question answering, novelty detection, and information provenance. Statistical trans­lation models are appropriate for tasks where the sentence to be retrieved benefits from the addition of related terms and synonyms. The context of a sentence affects its meaning, and smoothing from the local context of the sentence improves retrieval. A brief investigation of conditional models for sentence retrieval suggests conditional models outperform language modeling approaches, for some tasks. This book is addressed to students and professionals working on language technology systems that are dependent on sentence or passage retrieval.

Biographie de l'auteur

Postdoctoral Researcher for Yahoo! Research in Barcelona. PhD in Computer Science, University of Massachusetts at Amherst, Center for Intelligent Information Retrieval.

Détails de l'édition

• Éditeur: VDM Verlag Dr. Mueller E.K.
• Date d'édition: 2008
• Langue: anglais
• ISBN 10: 3836437651
• ISBN 13: 9783836437653
• Reliure: Broché
• Nombre de pages: 184
• Coordonnées du fabricant: non disponible
• Personne responsable: non disponible