On the role of information retrieval and information extraction in question answering systems

Dan Moldovan, Mihai Surdeanu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Question Answering, the process of extracting answers to natural language questions is profoundly different from Information Retrieval (IR) or Information Extraction (IE). IR systems allow us to locate relevant documents that relate to a query, but do not specify exactly where the answers are. In IR, the documents of interest are fetched by matching query keywords to the index of the document collection. By contrast, IE systems extrat the information of interest provided the domain of extraction is well defined. In IE systems, the information of interest is in trie form of slot fillers of some predefined templates. The QA technology takes both IR and IE a step further, and provides specific and brief answers to open domain questions formulated naturally. This paper presents the major modules used to build IR, IE and QA systems and Shows similarities, differences and possible trade-offs between the three technologies.

Original languageEnglish (US)
Title of host publicationLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Pages129-147
Number of pages19
Volume2700
StatePublished - 2003
Externally publishedYes

Fingerprint

Information retrieval
Information retrieval systems
Fillers

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Moldovan, D., & Surdeanu, M. (2003). On the role of information retrieval and information extraction in question answering systems. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2700, pp. 129-147)

On the role of information retrieval and information extraction in question answering systems. / Moldovan, Dan; Surdeanu, Mihai.

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). Vol. 2700 2003. p. 129-147.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Moldovan, D & Surdeanu, M 2003, On the role of information retrieval and information extraction in question answering systems. in Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). vol. 2700, pp. 129-147.
Moldovan D, Surdeanu M. On the role of information retrieval and information extraction in question answering systems. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). Vol. 2700. 2003. p. 129-147
Moldovan, Dan ; Surdeanu, Mihai. / On the role of information retrieval and information extraction in question answering systems. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). Vol. 2700 2003. pp. 129-147
@inproceedings{10960dd60d8240cab88dab6ece477d06,
title = "On the role of information retrieval and information extraction in question answering systems",
abstract = "Question Answering, the process of extracting answers to natural language questions is profoundly different from Information Retrieval (IR) or Information Extraction (IE). IR systems allow us to locate relevant documents that relate to a query, but do not specify exactly where the answers are. In IR, the documents of interest are fetched by matching query keywords to the index of the document collection. By contrast, IE systems extrat the information of interest provided the domain of extraction is well defined. In IE systems, the information of interest is in trie form of slot fillers of some predefined templates. The QA technology takes both IR and IE a step further, and provides specific and brief answers to open domain questions formulated naturally. This paper presents the major modules used to build IR, IE and QA systems and Shows similarities, differences and possible trade-offs between the three technologies.",
author = "Dan Moldovan and Mihai Surdeanu",
year = "2003",
language = "English (US)",
volume = "2700",
pages = "129--147",
booktitle = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

}

TY - GEN

T1 - On the role of information retrieval and information extraction in question answering systems

AU - Moldovan, Dan

AU - Surdeanu, Mihai

PY - 2003

Y1 - 2003

N2 - Question Answering, the process of extracting answers to natural language questions is profoundly different from Information Retrieval (IR) or Information Extraction (IE). IR systems allow us to locate relevant documents that relate to a query, but do not specify exactly where the answers are. In IR, the documents of interest are fetched by matching query keywords to the index of the document collection. By contrast, IE systems extrat the information of interest provided the domain of extraction is well defined. In IE systems, the information of interest is in trie form of slot fillers of some predefined templates. The QA technology takes both IR and IE a step further, and provides specific and brief answers to open domain questions formulated naturally. This paper presents the major modules used to build IR, IE and QA systems and Shows similarities, differences and possible trade-offs between the three technologies.

AB - Question Answering, the process of extracting answers to natural language questions is profoundly different from Information Retrieval (IR) or Information Extraction (IE). IR systems allow us to locate relevant documents that relate to a query, but do not specify exactly where the answers are. In IR, the documents of interest are fetched by matching query keywords to the index of the document collection. By contrast, IE systems extrat the information of interest provided the domain of extraction is well defined. In IE systems, the information of interest is in trie form of slot fillers of some predefined templates. The QA technology takes both IR and IE a step further, and provides specific and brief answers to open domain questions formulated naturally. This paper presents the major modules used to build IR, IE and QA systems and Shows similarities, differences and possible trade-offs between the three technologies.

UR - http://www.scopus.com/inward/record.url?scp=23144446532&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23144446532&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2700

SP - 129

EP - 147

BT - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

ER -