SPINOZA VU: An NLP Pipeline for Cross Document TimeLines

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

This paper describes the system SPINOZA VU developed for the SemEval 2015 Task 4: Cross Document TimeLines. The system integrates output from the NewsReader Natural Language Processing pipeline and is designed following an entity based model. The poor performance of the submitted runs are mainly a consequence of error propagation. Nevertheless, the error analysis has shown that the interpretation module behind the system performs correctly. An out of competition version of the system has fixed some errors and obtained competitive
results. Therefore, we consider the system an important step towards a more complex task such as storyline extraction.
Original languageEnglish
Title of host publicationProceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)
Place of PublicationDenver, Colorado, USA
PublisherAssociation for Computational Linguistics
Pages786-790
ISBN (Print)9781941643402
Publication statusPublished - 2015
EventSemEval 2015 -
Duration: 4 Jun 20155 Jun 2015

Conference

ConferenceSemEval 2015
Period4/06/155/06/15

Fingerprint

Pipelines
Error analysis
Processing

Cite this

Caselli, T., Fokkens-Zwirello, A. S., Morante, R., & Vossen, P. T. J. M. (2015). SPINOZA VU: An NLP Pipeline for Cross Document TimeLines. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015) (pp. 786-790). Denver, Colorado, USA: Association for Computational Linguistics.
Caselli, T. ; Fokkens-Zwirello, A.S. ; Morante, R. ; Vossen, P.T.J.M. / SPINOZA VU: An NLP Pipeline for Cross Document TimeLines. Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015). Denver, Colorado, USA : Association for Computational Linguistics, 2015. pp. 786-790
@inproceedings{cee359d4321d4ac89346baf3efff4452,
title = "SPINOZA VU: An NLP Pipeline for Cross Document TimeLines",
abstract = "This paper describes the system SPINOZA VU developed for the SemEval 2015 Task 4: Cross Document TimeLines. The system integrates output from the NewsReader Natural Language Processing pipeline and is designed following an entity based model. The poor performance of the submitted runs are mainly a consequence of error propagation. Nevertheless, the error analysis has shown that the interpretation module behind the system performs correctly. An out of competition version of the system has fixed some errors and obtained competitiveresults. Therefore, we consider the system an important step towards a more complex task such as storyline extraction.",
author = "T. Caselli and A.S. Fokkens-Zwirello and R. Morante and P.T.J.M. Vossen",
year = "2015",
language = "English",
isbn = "9781941643402",
pages = "786--790",
booktitle = "Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)",
publisher = "Association for Computational Linguistics",

}

Caselli, T, Fokkens-Zwirello, AS, Morante, R & Vossen, PTJM 2015, SPINOZA VU: An NLP Pipeline for Cross Document TimeLines. in Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015). Association for Computational Linguistics, Denver, Colorado, USA, pp. 786-790, SemEval 2015, 4/06/15.

SPINOZA VU: An NLP Pipeline for Cross Document TimeLines. / Caselli, T.; Fokkens-Zwirello, A.S.; Morante, R.; Vossen, P.T.J.M.

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015). Denver, Colorado, USA : Association for Computational Linguistics, 2015. p. 786-790.

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - SPINOZA VU: An NLP Pipeline for Cross Document TimeLines

AU - Caselli, T.

AU - Fokkens-Zwirello, A.S.

AU - Morante, R.

AU - Vossen, P.T.J.M.

PY - 2015

Y1 - 2015

N2 - This paper describes the system SPINOZA VU developed for the SemEval 2015 Task 4: Cross Document TimeLines. The system integrates output from the NewsReader Natural Language Processing pipeline and is designed following an entity based model. The poor performance of the submitted runs are mainly a consequence of error propagation. Nevertheless, the error analysis has shown that the interpretation module behind the system performs correctly. An out of competition version of the system has fixed some errors and obtained competitiveresults. Therefore, we consider the system an important step towards a more complex task such as storyline extraction.

AB - This paper describes the system SPINOZA VU developed for the SemEval 2015 Task 4: Cross Document TimeLines. The system integrates output from the NewsReader Natural Language Processing pipeline and is designed following an entity based model. The poor performance of the submitted runs are mainly a consequence of error propagation. Nevertheless, the error analysis has shown that the interpretation module behind the system performs correctly. An out of competition version of the system has fixed some errors and obtained competitiveresults. Therefore, we consider the system an important step towards a more complex task such as storyline extraction.

M3 - Conference contribution

SN - 9781941643402

SP - 786

EP - 790

BT - Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

PB - Association for Computational Linguistics

CY - Denver, Colorado, USA

ER -

Caselli T, Fokkens-Zwirello AS, Morante R, Vossen PTJM. SPINOZA VU: An NLP Pipeline for Cross Document TimeLines. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015). Denver, Colorado, USA: Association for Computational Linguistics. 2015. p. 786-790