U-Compare Co-reference Identification service

Handle:	https://hdl.handle.net/21.11129/0000-000B-D359-3 (persistent URL to this page)
URL:	http://nactem001.mib.man.ac.uk:8080/UCompareWebServices/Coreference_TTL_UAIC

Web service created by exporting UIMA-based workflow from the U-Compare text mining system.
Functionality: Identifies co-reference chains in plain text. Also identifies sentences, tokens with parts-of-speech and lemmas, and NP chunks
Tools in workflow: TTL-Tokenizer (RACAI, Romania), TTL-Tagger (RACAI, Romania), TTL-Lemmatizer (RACAI, Romania), UAIC-NPChunker (UAIC, Romania), UAIC-RARE (UAIC, Romania)
NOTE: The licence provided covers the web service only. Tools used to create the workflow may have their own licences

Contact Resource Maintainer

DistributionLicence

Proprietary

Restrictions: Academic - Non Commercial Use, Attribution

User Nature: Academic

Download location: hidden

Distribution Access/Medium: Accessible Through Interface, Web Executable

Execution location: hidden

Attribution Details: The U-Compare Co-reference Identification service is provided and hosted by the National Centre for Text Mining, School of Computer Science, University of Manchester

Licensors:

University of Manchester

School of Computer Science

University of Manchester

[javascript protected email address]

Distribution rights holders:

University of Manchester

School of Computer Science

University of Manchester

[javascript protected email address]

IPR Holder

University of Manchester

School of Computer Science

University of Manchester

[javascript protected email address]

Contact Person

Sophia Ananiadou

University of Manchester

Professor

[javascript protected email address]

School of Computer Science

[javascript protected email address]

Tool/Service

Service Web service

Language Dependent

Input

Media type: Text

Resource type: Corpus

Modality: Written Language

Language: Romanian

Character encoding: UTF - 8

Output

Media type: Text

Resource type: Corpus

Modality: Written Language

Language: Romanian

Character encoding: UTF - 8

Annotation type: Discourse Annotation - Coreference, Lemmatization, Morphosyntactic Annotation - Pos Tagging, Structural Annotation, Syntactic Annotation - Shallow Parsing

Annotation format: XML

Segmentation level: Phrase, Sentence, Word, Word Group

Operation

Operating system: Os - Independent

Resource Creation

Resource Creator

University of Manchester

School of Computer Science

University of Manchester

[javascript protected email address]

Funding Project

METANET4U - Enhancing the Linguistic Infrastructure of Europe (METANET4U)