Reviewing and Evaluating Automatic Term Recognition Techniques

Ioannis Korkontzelos; Ioannis P. Klapaftis; Suresh Manandhar

doi:10.1007/978-3-540-85287-2_24

Reviewing and Evaluating Automatic Term Recognition Techniques

Ioannis Korkontzelos, Ioannis P. Klapaftis, Suresh Manandhar

Computer Science

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

Abstract

Automatic Term Recognition (ATR) is defined as the task of identifying domain specific terms from technical corpora. Termhood-based approaches measure the degree that a candidate term refers to a domain specific concept. Unithood-based approaches measure the attachment strength of a candidate term constituents. These methods have been evaluated using different, often incompatible evaluation schemes and datasets. This paper provides an overview and a thorough evaluation of state-of-the-art ATR methods, under a common evaluation framework, i.e. corpora and evaluation method. Our contributions are two-fold: (1) We compare a number of different ATR methods, showing that termhood-based methods achieve in general superior performance. (2) We show that the number of independent occurrences of a candidate term is the most effective source for estimating term nestedness, improving ATR performance.

Original language	Undefined/Unknown
Pages	248-259
DOIs	https://doi.org/10.1007/978-3-540-85287-2_24
Publication status	Published - 2008

Access to Document

10.1007/978-3-540-85287-2_24

http://dx.doi.org/10.1007/978-3-540-85287-2_24

Cite this

@conference{3a39b74b7c17402d97193da5d6a86d93,

title = "Reviewing and Evaluating Automatic Term Recognition Techniques",

abstract = "Automatic Term Recognition (ATR) is defined as the task of identifying domain specific terms from technical corpora. Termhood-based approaches measure the degree that a candidate term refers to a domain specific concept. Unithood-based approaches measure the attachment strength of a candidate term constituents. These methods have been evaluated using different, often incompatible evaluation schemes and datasets. This paper provides an overview and a thorough evaluation of state-of-the-art ATR methods, under a common evaluation framework, i.e. corpora and evaluation method. Our contributions are two-fold: (1) We compare a number of different ATR methods, showing that termhood-based methods achieve in general superior performance. (2) We show that the number of independent occurrences of a candidate term is the most effective source for estimating term nestedness, improving ATR performance. ",

author = "Ioannis Korkontzelos and Klapaftis, {Ioannis P.} and Suresh Manandhar",

year = "2008",

doi = "10.1007/978-3-540-85287-2_24",

language = "Undefined/Unknown",

pages = "248--259",

}

TY - CONF

T1 - Reviewing and Evaluating Automatic Term Recognition Techniques

AU - Korkontzelos, Ioannis

AU - Klapaftis, Ioannis P.

AU - Manandhar, Suresh

PY - 2008

Y1 - 2008

N2 - Automatic Term Recognition (ATR) is defined as the task of identifying domain specific terms from technical corpora. Termhood-based approaches measure the degree that a candidate term refers to a domain specific concept. Unithood-based approaches measure the attachment strength of a candidate term constituents. These methods have been evaluated using different, often incompatible evaluation schemes and datasets. This paper provides an overview and a thorough evaluation of state-of-the-art ATR methods, under a common evaluation framework, i.e. corpora and evaluation method. Our contributions are two-fold: (1) We compare a number of different ATR methods, showing that termhood-based methods achieve in general superior performance. (2) We show that the number of independent occurrences of a candidate term is the most effective source for estimating term nestedness, improving ATR performance.

AB - Automatic Term Recognition (ATR) is defined as the task of identifying domain specific terms from technical corpora. Termhood-based approaches measure the degree that a candidate term refers to a domain specific concept. Unithood-based approaches measure the attachment strength of a candidate term constituents. These methods have been evaluated using different, often incompatible evaluation schemes and datasets. This paper provides an overview and a thorough evaluation of state-of-the-art ATR methods, under a common evaluation framework, i.e. corpora and evaluation method. Our contributions are two-fold: (1) We compare a number of different ATR methods, showing that termhood-based methods achieve in general superior performance. (2) We show that the number of independent occurrences of a candidate term is the most effective source for estimating term nestedness, improving ATR performance.

UR - http://www.scopus.com/inward/record.url?scp=52149106920&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-85287-2_24

DO - 10.1007/978-3-540-85287-2_24

M3 - Paper

SP - 248

EP - 259

ER -

Reviewing and Evaluating Automatic Term Recognition Techniques

Abstract

Access to Document

Other files and links

Cite this