CLARIN-NL - application/pdf

Syntax

Tool task

tokenisation

Country

Netherlands

Tool Type

local desktop

Research Phase

Enriching Data

Tool status

published

Input format

application/pdf

application/msword

text/folia+xml

text/plain

Output format

text/plain

Input Language

Dutch

Swedish

Russian

Spanish

Portuguese

English

German

French

Italian

Version

v0.13

Access Contact

Project Contact

/mailto:/

Creator Contact

Maarten van Gompel, Ko van der Sloot and Antal van den Bosch. 2017. Ucto: Unicode Tokenizer. version 0.9.6. Reference Guide. Technical Report, Jan 23, 2017.

Ko van der Sloot

Documentation

Maarten van Gompel, Ko van der Sloot, Antal van den Bosch (2012). Ucto: Unicode Tokeniser. Reference Guide. ILK Technical Report 12-05.

readme

releaseNotes

issueTracker

contIntegration

Source code

https://github.com/LanguageMachines/ucto

Resource

CMDI File Link

License

GNU GPL

Inventory Scope

local

Ucto Engine

root — Mon, 08 Apr 2019 08:38:55 +0000

https://raw.githubusercontent.com/LanguageMachines/ucto/master/logo.svg

Title

Ucto Tokeniser Engine

Description

The Ucto tokenisation engine is a language-independent engine that, given an external configuration file with tokenisation rules for a specifc language ,yields a tokenizer for that language that tokenizes text files: it separates words from punctuation, and splits sentences. This is one of the first tasks for almost any Natural Language Processing application. Ucto offers several other basic preprocessing steps such as changing case that you can all use to make your text suited for further processing such as indexing, part-of-speech tagging, or machine translation. The tokeniser engine is language independent. By supplying language-specific tokenisation rules in an external configuration file a tokeniser can be created for a specific language. Ucto comes with tokenization rules for English, Dutch, French, Italian, and Swedish; it is easily extensible to other languages. It recognizes dates, times, units, currencies, abbreviations. It recognizes paired quote spans, sentences, and paragraphs. It produces UTF8 encoding and NFC output normalization, optionally accepts other encodings as input. Optional conversion to all lowercase or uppercase. Ucto supports FoLiA XML.

Project

CLARIN-NL

CLARIAH-CORE

CLARIN National Project

CLARIN-NL

CLARIAH-CORE

CLARIN centre

none yet

Research domain

Linguistics

Linguistic Subject

Syntax

Tool task

tokenisation

Country

Netherlands

Tool Type

local desktop

Research Phase

Enriching Data

Tool status

published

Input format

application/pdf

application/msword

text/folia+xml

text/plain

Output format

text/plain

Input Language

Language independent

Version

v0.13

Access Contact

Project Contact

/mailto:/

Creator Contact

Maarten van Gompel, Ko van der Sloot and Antal van den Bosch. 2017. Ucto: Unicode Tokenizer. version 0.9.6. Reference Guide. Technical Report, Jan 23, 2017.

Ko van der Sloot

Documentation

Maarten van Gompel, Ko van der Sloot, Antal van den Bosch (2012). Ucto: Unicode Tokeniser. Reference Guide. ILK Technical Report 12-05.

readme

releaseNotes

issueTracker

contIntegration

Source code

https://github.com/LanguageMachines/ucto

Resource

CMDI File Link

License

GNU GPL

Inventory Scope

local

PICCL

root — Mon, 08 Apr 2019 08:38:55 +0000

Title

PICCL: Philosophical Integrator of Computational and Corpus Libraries

Description

PICCL is a set of workflows for corpus building through OCR, post-correction, modernization of historic language and Natural Language Processing. It combines Tesseract Optical Character Recognition, TICCL functionality and Frog functionality in a single pipeline. Tesseract offers Open Source software for optical character recognition. TICCL (Text Induced Corpus Clean-up) is a system that is designed to search a corpus for all existing variants of (potentially) all words occurring in the corpus. This corpus can be one text, or several, in one or more directories, located on one or more machines. TICCL creates word frequency lists, listing for each word type how often the word occurs in the corpus. These frequencies of the normalized word forms are the sum of the frequencies of the actual word forms found in the corpus. TICCL is a system that is intended to detect and correct typographical errors (misprints) and OCR errors (optical character recognition) in texts. When books or other texts are scanned from paper by a machine, that then turns these scans, i.e. images, into digital text files, errors occur. For instance, the letter combination `in' can be read as `m', and so the word `regeering' is incorrectly reproduced as `regeermg'. TICCL can be used to detect these errors and to suggest a correct form. Frog enriches textual documents with various linguistic annotations.

Project

CLARIN-NL

CLARIAH-CORE

Nederlab

CLARIN National Project

CLARIN-NL

CLARIAH-CORE

CLARIN centre

none yet

Research domain

Linguistics

Philosophy

Literary Studies

Religion Studies

History

Linguistic Subject

Orthography

Morphology

Syntax

Tool task

optical character recognition

orthographic normalisation

tokenisation

dependency parsing

shallow parsing

lemmatisation

morphological analysis

named entity recognition

part of speech tagging

Country

Netherlands

Tool Type

local desktop

Research Phase

Enriching Data

Tool status

published

Input format

application/pdf

image/tiff

text/plain

text/folia+xml

image/vnd.djvu

Output format

text/folia+xml

Input Language

Dutch

Swedish

Russian

Spanish

Portuguese

English

German

French

Italian

Finnish

Modern Greek

Classical Greek

Icelandic

German (Fraktur)

Latin

Romanian

Version

v0.6.4

Access Contact

Martin Reynaert

Project Contact

/mailto:/

Creator Contact

Martin Reynaert

Ko van der Sloot

Documentation

Information Page

readme

releaseNotes

issueTracker

contIntegration

Source code

https://github.com/LanguageMachines/piccl

Publications

Martin Reynaert, Maarten van Gompel, Ko van der Sloot and Antal van den Bosch. 2015. PICCL: Philosophical Integrator of Computational and Corpus Libraries. Proceedings of CLARIN Annual Conference 2015, pp. 75-79. Wrocław, Poland. http://www.nederlab.nl/cms/wp-content/uploads/2015/10/Reynaert_PICCL-Philosophical-Integrator-of-Computational-and-Corpus-Libraries.pdf

Resource

LandingPage

CMDI File Link

License

GNU GPL

Inventory Scope

local

TiCClops

root — Mon, 08 Apr 2019 08:38:55 +0000

Title

TiCClops: Text-Induced Corpus Clean-up online processing system

Description

TICCL (Text Induced Corpus Clean-up) is a system that is designed to search a corpus for all existing variants of (potentially) all words occurring in the corpus. This corpus can be one text, or several, in one or more directories, located on one or more machines. TICCL creates word frequency lists, listing for each word type how often the word occurs in the corpus. These frequencies of the normalized word forms are the sum of the frequencies of the actual word forms found in the corpus. TICCL is a system that is intended to detect and correct typographical errors (misprints) and OCR errors (optical character recognition) in texts. When books or other texts are scanned from paper by a machine, that then turns these scans, i.e. images, into digital text files, errors occur. For instance, the letter combination `in' can be read as `m', and so the word `regeering' is incorrectly reproduced as `regeermg'. TICCL can be used to detect these errors and to suggest a correct form. Text-Induced Corpus Clean-up (TICCL) was developed first as a prototype at the request of the Koninklijke Bibliotheek - The Hague (KB) and reworked into a production tool according to KB specifications (currently at production version 2.0) mainly during the second half of 2008. It is a fully functional environment for processing possibly very large corpora in order to largely remove the undesirable lexical variation in them. It has provisions for various input and output formats, is flexible and robust and has very high recall and acceptable precision. As a spelling variation detection system it is to the developer’s knowledge unique in making principled use of the input text as possible source for target output canonical forms. As such it is far less domain-sensitive than other approaches: the domain is largely covered by the input text collection. TICCL comes in two variants: one with a classic CLAM web application interface, and one with the PhilosTEI interface.

Project

TiCClops: Text-Induced Corpus Clean-up online processing system

CLARIN National Project

CLARIN-NL

CLARIN centre

Dutch Language Institute

Research domain

Linguistics

Linguistic Subject

Orthography

Tool task

corpus processing

orthographic normalisation

Country

Netherlands

Tool Type

web application

Research Phase

Enriching Data

Tool status

published

Input format

image/tiff

image/vnd.djvu

application/pdf

text/plain

text/xml

text/csv

Output format

text/xml

Input Language

Dutch

English

Finnish

French

German

German (Fraktur)

Classical Greek

Modern Greek

Icelandic

Italian

Latin

Polish

Portuguese

Russian

Spanish

Swedish

Access Contact

/mailto:servicedesk@ivdnt.org/

Institute for the Dutch Language

Project Contact

dr. Martin Reynaert

Creator Contact

dr. Martin Reynaert

Documentation

TICCLops User and Demonstrator Documentation

Source code

not specified

Original source

http://portal.clarin.nl/node/1914

Publications

Reynaert, M. (2008). All, and only, the errors: More complete and consistent spelling and OCR-error correction evaluation. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), Marrakech, Morocco.

Reynaert, M. (2010). Character confusion versus focus word-based correction of spelling and ocr variants in corpora. International Journal on Document Analysis and Recognition, pp 1-15, URL http://dx.doi.org/10.1007/s10032-010-0133-5

Resource

CMDI File Link

License

unknown

Inventory Scope

local

Frog

root — Mon, 08 Apr 2019 08:38:48 +0000

http://dev.clarin.nl/sites/default/files/froglogo.svg

Title

Frog: An advanced Natural Language Processing Suite for Dutch (Web Service and Application)

Description

Frog is an integration of memory-based natural language processing (NLP) modules developed for Dutch. It performs automatic linguistic enrichment such as part of speech tagging, lemmatisation, named entity recognition, shallow parsing, dependency parsing and morphological analysis. All NLP modules are based on TiMBL.

Project

CGN

CLARIN-NL

CLARIAH-CORE

CLARIN National Project

CLARIN-NL

CLARIAH-CORE

CLARIN centre

none yet

Research domain

Linguistics

Linguistic Subject

Syntax

Tool task

dependency parsing

shallow parsing

lemmatisation

morphological analysis

named entity recognition

part of speech tagging

tokenisation

Country

Netherlands

Tool Type

web application

Research Phase

Enriching Data

Tool status

published

Input format

application/pdf

application/msword

text/folia+xml

text/plain

Output format

text/csv

Input Language

Dutch

Version

v0.15

Access Contact

Project Contact

/mailto:/

Creator Contact