User Modeling for Adaptive Question Answering and Information Retrieval

Silvia Quarteroni; Suresh Manandhar

User Modeling for Adaptive Question Answering and Information Retrieval

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

Most question answering (QA) and information retrieval (IR) systems are insensitive to different users’ needs and preferences, and also to the existence of multiple, complex or controversial answers. We propose the notion of adaptivity in QA and IR by introducing a hybrid QA-IR system based on a user model. Our current prototype filters and re-ranks the query results returned by a search engine according to their reading level. This is particularly useful in school environments, where it is most needed to adjust the presentation of complex information to the pupils’ level of understanding.

Original language	Undefined/Unknown
Pages	776-781
Publication status	Published - 2006

Cite this

@conference{5cd4c6266ac3430691d8dd3b2215c445,

title = "User Modeling for Adaptive Question Answering and Information Retrieval",

abstract = "Most question answering (QA) and information retrieval (IR) systems are insensitive to different users{\textquoteright} needs and preferences, and also to the existence of multiple, complex or controversial answers. We propose the notion of adaptivity in QA and IR by introducing a hybrid QA-IR system based on a user model. Our current prototype filters and re-ranks the query results returned by a search engine according to their reading level. This is particularly useful in school environments, where it is most needed to adjust the presentation of complex information to the pupils{\textquoteright} level of understanding.",

author = "Silvia Quarteroni and Suresh Manandhar",

year = "2006",

language = "Undefined/Unknown",

pages = "776--781",

}

TY - CONF

T1 - User Modeling for Adaptive Question Answering and Information Retrieval

AU - Quarteroni, Silvia

AU - Manandhar, Suresh

PY - 2006

Y1 - 2006

N2 - Most question answering (QA) and information retrieval (IR) systems are insensitive to different users’ needs and preferences, and also to the existence of multiple, complex or controversial answers. We propose the notion of adaptivity in QA and IR by introducing a hybrid QA-IR system based on a user model. Our current prototype filters and re-ranks the query results returned by a search engine according to their reading level. This is particularly useful in school environments, where it is most needed to adjust the presentation of complex information to the pupils’ level of understanding.

AB - Most question answering (QA) and information retrieval (IR) systems are insensitive to different users’ needs and preferences, and also to the existence of multiple, complex or controversial answers. We propose the notion of adaptivity in QA and IR by introducing a hybrid QA-IR system based on a user model. Our current prototype filters and re-ranks the query results returned by a search engine according to their reading level. This is particularly useful in school environments, where it is most needed to adjust the presentation of complex information to the pupils’ level of understanding.

M3 - Paper

SP - 776

EP - 781

ER -