Advanced Structural Representations for Question Classification and Answer Re-ranking

Silvia Quarteroni; Alessandro Moschitti; Suresh Manandhar; Roberto Basili; Giambattista Amati; Claudio Carpineto; Giovanni Romano

doi:10.1007/978-3-540-71496-5_23

Advanced Structural Representations for Question Classification and Answer Re-ranking

Silvia Quarteroni, Alessandro Moschitti, Suresh Manandhar, Roberto Basili, Giambattista Amati, Claudio Carpineto, Giovanni Romano

Computer Science

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

Abstract

In this paper, we study novel structures to represent information in three vital tasks in question answering: question classification, answer classification and answer reranking. We define a new tree structure called PAS to represent predicate-argument relations, as well as a new kernel function to exploit its representative power. Our experiments with Support Vector Machines and several tree kernel functions suggest that syntactic information helps specific task as question classification, whereas, when data sparseness is higher as in answer classification, studying coarse semantic information like PAS is a promising research area.

Original language	Undefined/Unknown
Pages	234-245
DOIs	https://doi.org/10.1007/978-3-540-71496-5_23
Publication status	Published - 2007

Access to Document

10.1007/978-3-540-71496-5_23

http://dx.doi.org/10.1007/978-3-540-71496-5_23

Cite this

@conference{d5652a2aa67c43d9acd3f86574a01447,

title = "Advanced Structural Representations for Question Classification and Answer Re-ranking",

abstract = "In this paper, we study novel structures to represent information in three vital tasks in question answering: question classification, answer classification and answer reranking. We define a new tree structure called PAS to represent predicate-argument relations, as well as a new kernel function to exploit its representative power. Our experiments with Support Vector Machines and several tree kernel functions suggest that syntactic information helps specific task as question classification, whereas, when data sparseness is higher as in answer classification, studying coarse semantic information like PAS is a promising research area. ",

author = "Silvia Quarteroni and Alessandro Moschitti and Suresh Manandhar and Roberto Basili and Giambattista Amati and Claudio Carpineto and Giovanni Romano",

year = "2007",

doi = "10.1007/978-3-540-71496-5_23",

language = "Undefined/Unknown",

pages = "234--245",

}

TY - CONF

T1 - Advanced Structural Representations for Question Classification and Answer Re-ranking

AU - Quarteroni, Silvia

AU - Moschitti, Alessandro

AU - Manandhar, Suresh

AU - Basili, Roberto

AU - Amati, Giambattista

AU - Carpineto, Claudio

AU - Romano, Giovanni

PY - 2007

Y1 - 2007

N2 - In this paper, we study novel structures to represent information in three vital tasks in question answering: question classification, answer classification and answer reranking. We define a new tree structure called PAS to represent predicate-argument relations, as well as a new kernel function to exploit its representative power. Our experiments with Support Vector Machines and several tree kernel functions suggest that syntactic information helps specific task as question classification, whereas, when data sparseness is higher as in answer classification, studying coarse semantic information like PAS is a promising research area.

AB - In this paper, we study novel structures to represent information in three vital tasks in question answering: question classification, answer classification and answer reranking. We define a new tree structure called PAS to represent predicate-argument relations, as well as a new kernel function to exploit its representative power. Our experiments with Support Vector Machines and several tree kernel functions suggest that syntactic information helps specific task as question classification, whereas, when data sparseness is higher as in answer classification, studying coarse semantic information like PAS is a promising research area.

U2 - 10.1007/978-3-540-71496-5_23

DO - 10.1007/978-3-540-71496-5_23

M3 - Paper

SP - 234

EP - 245

ER -