Proceedings of the Third Workshop on Analytics for Noisy Unstructured Text Data 2009
DOI: 10.1145/1568296.1568307
|View full text |Cite
|
Sign up to set email alerts
|

Accessing the content of Greek historical documents

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2011
2011
2016
2016

Publication Types

Select...
4
2
1

Relationship

1
6

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 14 publications
0
5
0
Order By: Relevance
“…To this end, an alternative method for accessing the content of historical machine-printed texts based on word spotting aided by Natural Language Processing techniques is proposed in Kesidis et al (2011). An initial experimentation is also reported in Kesidis et al (2009). The method consists of the following five steps:…”
Section: An Alternative Methods For Accessing the Content Of The Textsmentioning
confidence: 99%
See 2 more Smart Citations
“…To this end, an alternative method for accessing the content of historical machine-printed texts based on word spotting aided by Natural Language Processing techniques is proposed in Kesidis et al (2011). An initial experimentation is also reported in Kesidis et al (2009). The method consists of the following five steps:…”
Section: An Alternative Methods For Accessing the Content Of The Textsmentioning
confidence: 99%
“…That particular period was chosen for this first implementation because the language in which the texts are written reflects an early stage of Modern Greek and is indicative of the evolution of the Greek language, as it incorporates elements from Ancient, Medieval and Modern Greek. An initial version of these tools is described in Kesidis et al (2009).…”
Section: Natural Language Processing Tools For Older Varieties Of Greekmentioning
confidence: 99%
See 1 more Smart Citation
“…If we assume we have extracted a meaningful set of feature vectors from a set of documents, the most common way to measure differences between them is the Euclidean ( [8], [9]) or the L1 distance [10]. With template matching based approaches the similarity among images is computed by a simple value comparison [11] or using a specific dissimilarity function [12].…”
Section: A Similarity Measuresmentioning
confidence: 99%
“…Commercial OCR systems do exist for monotonic, typewritten Greek, but processing of polytonic printed text is known to give poor results [132]. Word spotting techniques that use learning-free, zoning features are proposed in [132,299]. The elaboration of recognition or spotting techniques for polytonic Greek handwritten texts remains a challenge largely unaddressed.…”
Section: Using Attributes For Kws In Polytonic Greek Documentsmentioning
confidence: 99%