Can click patterns across user's query logs predict answers to definition questions?

Resultado de la investigación: Contribución a los tipos de informe/libroContribución a la conferenciarevisión exhaustiva

Resumen

In this paper, we examined click patterns produced by users of Yahoo search engine when prompting definition questions. Regularities across these click patterns are then utilized for constructing a large and heterogeneous training corpus for answer ranking. In a nutshell, answers are extracted from clicked web-snippets originating from any class of web-site, including Knowledge Bases (KBs). On the other hand, nonanswers are acquired from redundant pieces of text across web-snippets. The effectiveness of this corpus was assessed via training two state-of-The-Art models, wherewith answers to unseen queries were distinguished. These testing queries were also submitted by search engine users, and their answer candidates were taken from their respective returned web-snippets. This corpus helped both techniques to finish with an accuracy higher than 70%, and to predict over 85% of the answers clicked by users. In particular, our results underline the importance of non-KB training data.

Idioma originalInglés
Título de la publicación alojadaEACL 2012 - 13th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings
EditorialAssociation for Computational Linguistics (ACL)
Páginas99-108
Número de páginas10
ISBN (versión digital)9781937284190
EstadoPublicada - 1 ene 2012
Evento13th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2012 - Avignon, Francia
Duración: 23 abr 201227 abr 2012

Conferencia

Conferencia13th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2012
País/TerritorioFrancia
CiudadAvignon
Período23/04/1227/04/12

Áreas temáticas de ASJC Scopus

  • Teoría computacional y matemáticas
  • Software

Huella

Profundice en los temas de investigación de 'Can click patterns across user's query logs predict answers to definition questions?'. En conjunto forman una huella única.

Citar esto