DIT frequency based incremental attribute selection for GRE.

John Kelleher

doi:10.21427/yy9f-y443

DIT frequency based incremental attribute selection for GRE.

John Kelleher

Research output: Contribution to journal › Article › peer-review

Abstract

The DIT system uses an incremental greedy search to generate descriptions, (similar to the incremental algorithm described in (Dale and Reiter, 1995) ) incremental algorithm). The selection of the next attribute to be tested for inclusion in the description is ordered by the absolute frequency of each attribute in the training corpus. Attributes are selected in descending order of frequency (i.e. the attribute that occurred most frequently in the training corpus is selected first).

Original language	English
Journal	Proceedings of the MT Summit XI Workshop Using Corpora for Natural Language Generation: Language Generation and Machine Translation (UNLG+MT)
DOIs	https://doi.org/10.21427/yy9f-y443
Publication status	Published - 1 Jan 2007
Externally published	Yes

Keywords

DIT system
incremental greedy search
descriptions
incremental algorithm
attribute selection
training corpus
frequency

Access to Document

10.21427/yy9f-y443Licence: CC BY-NC-SA

Cite this

@article{4bf489d3565b4ba096aa5674711ffa75,

title = "DIT frequency based incremental attribute selection for GRE.",

abstract = "The DIT system uses an incremental greedy search to generate descriptions, (similar to the incremental algorithm described in (Dale and Reiter, 1995) ) incremental algorithm). The selection of the next attribute to be tested for inclusion in the description is ordered by the absolute frequency of each attribute in the training corpus. Attributes are selected in descending order of frequency (i.e. the attribute that occurred most frequently in the training corpus is selected first).",

keywords = "DIT system, incremental greedy search, descriptions, incremental algorithm, attribute selection, training corpus, frequency",

author = "John Kelleher",

year = "2007",

month = jan,

day = "1",

doi = "10.21427/yy9f-y443",

language = "English",

journal = "Proceedings of the MT Summit XI Workshop Using Corpora for Natural Language Generation: Language Generation and Machine Translation (UNLG+MT)",

}

TY - JOUR

T1 - DIT frequency based incremental attribute selection for GRE.

AU - Kelleher, John

PY - 2007/1/1

Y1 - 2007/1/1

N2 - The DIT system uses an incremental greedy search to generate descriptions, (similar to the incremental algorithm described in (Dale and Reiter, 1995) ) incremental algorithm). The selection of the next attribute to be tested for inclusion in the description is ordered by the absolute frequency of each attribute in the training corpus. Attributes are selected in descending order of frequency (i.e. the attribute that occurred most frequently in the training corpus is selected first).

AB - The DIT system uses an incremental greedy search to generate descriptions, (similar to the incremental algorithm described in (Dale and Reiter, 1995) ) incremental algorithm). The selection of the next attribute to be tested for inclusion in the description is ordered by the absolute frequency of each attribute in the training corpus. Attributes are selected in descending order of frequency (i.e. the attribute that occurred most frequently in the training corpus is selected first).

KW - DIT system

KW - incremental greedy search

KW - descriptions

KW - incremental algorithm

KW - attribute selection

KW - training corpus

KW - frequency

U2 - 10.21427/yy9f-y443

DO - 10.21427/yy9f-y443

M3 - Article

JO - Proceedings of the MT Summit XI Workshop Using Corpora for Natural Language Generation: Language Generation and Machine Translation (UNLG+MT)

JF - Proceedings of the MT Summit XI Workshop Using Corpora for Natural Language Generation: Language Generation and Machine Translation (UNLG+MT)

ER -