SPINOZA VU: An NLP Pipeline for Cross Document TimeLines

T. Caselli; A.S. Fokkens-Zwirello; R. Morante; P.T.J.M. Vossen

SPINOZA VU: An NLP Pipeline for Cross Document TimeLines

T. Caselli, A.S. Fokkens-Zwirello, R. Morante, P.T.J.M. Vossen

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-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 language	English
Title of host publication	Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)
Place of Publication	Denver, Colorado, USA
Publisher	Association for Computational Linguistics
Pages	786-790
ISBN (Print)	9781941643402
Publication status	Published - 2015
Event	SemEval 2015 - Duration: 4 Jun 2015 → 5 Jun 2015

Conference

Conference	SemEval 2015
Period	4/06/15 → 5/06/15

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

http://alt.qcri.org/semeval2015/cdrom/pdf/SemEval133.pdf

Persistent URL (handle)

Persistent link

Cite this

@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",

note = "SemEval 2015 ; Conference date: 04-06-2015 Through 05-06-2015",

}

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. <http://alt.qcri.org/semeval2015/cdrom/pdf/SemEval133.pdf>

SPINOZA VU: An NLP Pipeline for Cross Document TimeLines. / Caselli, T.; Fokkens-Zwirello, A.S.; Morante, R. et al.
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 proceeding › Conference contribution › Academic › peer-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

T2 - SemEval 2015

Y2 - 4 June 2015 through 5 June 2015

ER -

SPINOZA VU: An NLP Pipeline for Cross Document TimeLines

Abstract

Conference

UN SDGs

Access to Document

Persistent URL (handle)

Fingerprint

Cite this