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.

LiMoSINe Pipeline: Multilingual UIMA-based NLP Platform / Uryupina, Olga; Barbara, Plank; Barlacchi, Gianni; Francisco, J; Valverde, Albacete; Manos, Tsagkias; Uva, Antonio. - ELETTRONICO. - (2016), pp. 157-162. [10.18653/v1/P16-4027]

LiMoSINe Pipeline: Multilingual UIMA-based NLP Platform

Uryupina, Olga;Barlacchi, Gianni;Uva, Antonio
2016

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.
Proceedings of ACL-2016 System Demonstrations
Stroudsburg PA
Association for Computational Linguistics (ACL)
Uryupina, Olga; Barbara, Plank; Barlacchi, Gianni; Francisco, J; Valverde, Albacete; Manos, Tsagkias; Uva, Antonio
LiMoSINe Pipeline: Multilingual UIMA-based NLP Platform / Uryupina, Olga; Barbara, Plank; Barlacchi, Gianni; Francisco, J; Valverde, Albacete; Manos, Tsagkias; Uva, Antonio. - ELETTRONICO. - (2016), pp. 157-162. [10.18653/v1/P16-4027]
File in questo prodotto:
File Dimensione Formato  
LiMoSINe .pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 297.23 kB
Formato Adobe PDF
297.23 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11572/169989
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact