LiMoSINe pipeline

Multilingual UIMA-based NLP platform

Olga Uryupina, Barbara Plank, Gianni Barlacchi, Francisco Valverde Albacete, Manos Tsagkias, Antonio Uva, Alessandro Moschitti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We present a robust and efficient parallelizable multilingual UIMA-based platform for automatically annotating textual inputs with different layers of linguistic description, ranging from surface level phenomena all the way down to deep discourse-level information. In particular, given an input text, the pipeline extracts: sentences and tokens; entity mentions; syntactic information; opinionated expressions; relations between entity mentions; co-reference chains and wikified entities. The system is available in two versions: a standalone distribution enables design and optimization of userspecific sub-modules, whereas a server-client distribution allows for straightforward highperformance NLP processing, reducing the engineering cost for higher-level tasks.

Original languageEnglish
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations
PublisherAssociation for Computational Linguistics (ACL)
Pages157-162
Number of pages6
ISBN (Electronic)9781510827615
Publication statusPublished - 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: 7 Aug 201612 Aug 2016

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period7/8/1612/8/16

Fingerprint

Syntactics
Linguistics
Servers
Pipelines
Processing
Costs
engineering
linguistics
discourse
costs
Entity
Natural Language Processing

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Linguistics and Language
  • Language and Linguistics

Cite this

Uryupina, O., Plank, B., Barlacchi, G., Albacete, F. V., Tsagkias, M., Uva, A., & Moschitti, A. (2016). LiMoSINe pipeline: Multilingual UIMA-based NLP platform. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations (pp. 157-162). Association for Computational Linguistics (ACL).

LiMoSINe pipeline : Multilingual UIMA-based NLP platform. / Uryupina, Olga; Plank, Barbara; Barlacchi, Gianni; Albacete, Francisco Valverde; Tsagkias, Manos; Uva, Antonio; Moschitti, Alessandro.

54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations. Association for Computational Linguistics (ACL), 2016. p. 157-162.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Uryupina, O, Plank, B, Barlacchi, G, Albacete, FV, Tsagkias, M, Uva, A & Moschitti, A 2016, LiMoSINe pipeline: Multilingual UIMA-based NLP platform. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations. Association for Computational Linguistics (ACL), pp. 157-162, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 7/8/16.
Uryupina O, Plank B, Barlacchi G, Albacete FV, Tsagkias M, Uva A et al. LiMoSINe pipeline: Multilingual UIMA-based NLP platform. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations. Association for Computational Linguistics (ACL). 2016. p. 157-162
Uryupina, Olga ; Plank, Barbara ; Barlacchi, Gianni ; Albacete, Francisco Valverde ; Tsagkias, Manos ; Uva, Antonio ; Moschitti, Alessandro. / LiMoSINe pipeline : Multilingual UIMA-based NLP platform. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations. Association for Computational Linguistics (ACL), 2016. pp. 157-162
@inproceedings{ae15437c35484b2992c64ae10c799aed,
title = "LiMoSINe pipeline: Multilingual UIMA-based NLP platform",
abstract = "We present a robust and efficient parallelizable multilingual UIMA-based platform for automatically annotating textual inputs with different layers of linguistic description, ranging from surface level phenomena all the way down to deep discourse-level information. In particular, given an input text, the pipeline extracts: sentences and tokens; entity mentions; syntactic information; opinionated expressions; relations between entity mentions; co-reference chains and wikified entities. The system is available in two versions: a standalone distribution enables design and optimization of userspecific sub-modules, whereas a server-client distribution allows for straightforward highperformance NLP processing, reducing the engineering cost for higher-level tasks.",
author = "Olga Uryupina and Barbara Plank and Gianni Barlacchi and Albacete, {Francisco Valverde} and Manos Tsagkias and Antonio Uva and Alessandro Moschitti",
year = "2016",
language = "English",
pages = "157--162",
booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - LiMoSINe pipeline

T2 - Multilingual UIMA-based NLP platform

AU - Uryupina, Olga

AU - Plank, Barbara

AU - Barlacchi, Gianni

AU - Albacete, Francisco Valverde

AU - Tsagkias, Manos

AU - Uva, Antonio

AU - Moschitti, Alessandro

PY - 2016

Y1 - 2016

N2 - We present a robust and efficient parallelizable multilingual UIMA-based platform for automatically annotating textual inputs with different layers of linguistic description, ranging from surface level phenomena all the way down to deep discourse-level information. In particular, given an input text, the pipeline extracts: sentences and tokens; entity mentions; syntactic information; opinionated expressions; relations between entity mentions; co-reference chains and wikified entities. The system is available in two versions: a standalone distribution enables design and optimization of userspecific sub-modules, whereas a server-client distribution allows for straightforward highperformance NLP processing, reducing the engineering cost for higher-level tasks.

AB - We present a robust and efficient parallelizable multilingual UIMA-based platform for automatically annotating textual inputs with different layers of linguistic description, ranging from surface level phenomena all the way down to deep discourse-level information. In particular, given an input text, the pipeline extracts: sentences and tokens; entity mentions; syntactic information; opinionated expressions; relations between entity mentions; co-reference chains and wikified entities. The system is available in two versions: a standalone distribution enables design and optimization of userspecific sub-modules, whereas a server-client distribution allows for straightforward highperformance NLP processing, reducing the engineering cost for higher-level tasks.

UR - http://www.scopus.com/inward/record.url?scp=85016513145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016513145&partnerID=8YFLogxK

M3 - Conference contribution

SP - 157

EP - 162

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - System Demonstrations

PB - Association for Computational Linguistics (ACL)

ER -