Guardado en:
Detalles Bibliográficos
Autores principales: Litvinov, Oleg, Sekulić, Ivan, Aliannejadi, Mohammad, Crestani, Fabio
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.04524
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911751849639936
author Litvinov, Oleg
Sekulić, Ivan
Aliannejadi, Mohammad
Crestani, Fabio
author_facet Litvinov, Oleg
Sekulić, Ivan
Aliannejadi, Mohammad
Crestani, Fabio
contents Clarifying user's information needs is an essential component of modern search systems. While most of the approaches for constructing clarifying prompts rely on query facets, the impact of the quality of the facets is relatively unexplored. In this work, we concentrate on facet quality through the notion of facet coherency and assess its importance for overall usefulness for clarification in search. We find that existing evaluation procedures do not account for facet coherency, as evident by the poor correlation of coherency with automated metrics. Moreover, we propose a coherency classifier and assess the prevalence of incoherent facets in a well-established dataset on clarification. Our findings can serve as motivation for future work on the topic.
format Preprint
id arxiv_https___arxiv_org_abs_2401_04524
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analyzing Coherency in Facet-based Clarification Prompt Generation for Search
Litvinov, Oleg
Sekulić, Ivan
Aliannejadi, Mohammad
Crestani, Fabio
Information Retrieval
Clarifying user's information needs is an essential component of modern search systems. While most of the approaches for constructing clarifying prompts rely on query facets, the impact of the quality of the facets is relatively unexplored. In this work, we concentrate on facet quality through the notion of facet coherency and assess its importance for overall usefulness for clarification in search. We find that existing evaluation procedures do not account for facet coherency, as evident by the poor correlation of coherency with automated metrics. Moreover, we propose a coherency classifier and assess the prevalence of incoherent facets in a well-established dataset on clarification. Our findings can serve as motivation for future work on the topic.
title Analyzing Coherency in Facet-based Clarification Prompt Generation for Search
topic Information Retrieval
url https://arxiv.org/abs/2401.04524