A Two-Step Named Entity Recognizer for Open-Domain Search Queries

Andreas Eiselt, Alejandro Figueroa

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

13 Citas (SciVal)

Resumen

Named entity recognition in queries is the task of identifying sequences of terms in search queries that refer to a unique concept. This problem is catching increasing attention, since the lack of context in short queries makes this task difficult for full-text off-the-shelf named entity recognizers. In this paper, we propose to deal with this problem in a two-step fashion. The first step classifies each query term as token or part of a named entity. The second step takes advantage of these binary labels for categorizing query terms into a pre-defined set of 28 named entity classes. Our results show that our two-step strategy is promising by outperforming a one-step traditional baseline by more than 10%.

Idioma originalInglés
Título de la publicación alojada6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference
EditoresRuslan Mitkov, Jong C. Park
EditorialAsian Federation of Natural Language Processing
Páginas829-833
Número de páginas5
ISBN (versión digital)9784990734800
EstadoPublicada - 2013
Publicado de forma externa
Evento6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Nagoya, Japón
Duración: 14 oct. 2013 → …

Serie de la publicación

Nombre6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference

Conferencia

Conferencia6th International Joint Conference on Natural Language Processing, IJCNLP 2013
País/TerritorioJapón
CiudadNagoya
Período14/10/13 → …

Áreas temáticas de ASJC Scopus

  • Inteligencia artificial
  • Software

Huella

Profundice en los temas de investigación de 'A Two-Step Named Entity Recognizer for Open-Domain Search Queries'. En conjunto forman una huella única.

Citar esto