Difference between revisions of "Detecting Korean Hedge Sentences in Wikipedia Documents"
(Wikilinks) |
(Infobox work) |
||
| Line 1: | Line 1: | ||
| + | {{Infobox work | ||
| + | | title = Detecting Korean Hedge Sentences in Wikipedia Documents | ||
| + | | date = 2012 | ||
| + | | authors = [[Shin-Jae Kang]]<br />[[Ju-Seok Jeong]]<br />[[In-Su Kang]] | ||
| + | | doi = 10.1007/978-3-642-32645-5_91 | ||
| + | | link = https://link.springer.com/content/pdf/10.1007%2F978-3-642-32645-5_91.pdf | ||
| + | }} | ||
'''Detecting Korean Hedge Sentences in Wikipedia Documents''' - scientific work related to [[Wikipedia quality]] published in 2012, written by [[Shin-Jae Kang]], [[Ju-Seok Jeong]] and [[In-Su Kang]]. | '''Detecting Korean Hedge Sentences in Wikipedia Documents''' - scientific work related to [[Wikipedia quality]] published in 2012, written by [[Shin-Jae Kang]], [[Ju-Seok Jeong]] and [[In-Su Kang]]. | ||
== Overview == | == Overview == | ||
In this paper authors propose automatic hedge detection methods for Korean. Authors select sentential contextual [[features]] adjusted for Korean, and used supervised machine-learning algorithms to train models to detect hedges in [[Wikipedia]] documents. Authors SVM-based model achieved an F1-score of 90.8% for Korean. | In this paper authors propose automatic hedge detection methods for Korean. Authors select sentential contextual [[features]] adjusted for Korean, and used supervised machine-learning algorithms to train models to detect hedges in [[Wikipedia]] documents. Authors SVM-based model achieved an F1-score of 90.8% for Korean. | ||
Revision as of 09:05, 6 January 2020
Authors | Shin-Jae Kang Ju-Seok Jeong In-Su Kang |
|---|---|
Publication date | 2012 |
DOI | 10.1007/978-3-642-32645-5_91 |
Links | Original |
Detecting Korean Hedge Sentences in Wikipedia Documents - scientific work related to Wikipedia quality published in 2012, written by Shin-Jae Kang, Ju-Seok Jeong and In-Su Kang.
Overview
In this paper authors propose automatic hedge detection methods for Korean. Authors select sentential contextual features adjusted for Korean, and used supervised machine-learning algorithms to train models to detect hedges in Wikipedia documents. Authors SVM-based model achieved an F1-score of 90.8% for Korean.
