In this paper, we present a multi-featured supervised automatic keyword extraction system. We extracted salient semantic features which are descriptive of candidate keyphrases, a Random Forest classifier was used for training. The system achieved an accuracy of 58.3 % precision and has shown to outperform two top performing systems when benchmarked on a crowdsourced dataset. Furthermore, our approach achieved a personal best Precision and F-measure score of 32.7 and 25.5 respectively on the Semeval Keyphrase extraction challenge dataset. The paper describes the approaches used as well as the result obtained.1 © 2016 ACM.

A supervised keyphrase extraction system

DI CARO, Luigi;BOELLA, Guido
2016-01-01

Abstract

In this paper, we present a multi-featured supervised automatic keyword extraction system. We extracted salient semantic features which are descriptive of candidate keyphrases, a Random Forest classifier was used for training. The system achieved an accuracy of 58.3 % precision and has shown to outperform two top performing systems when benchmarked on a crowdsourced dataset. Furthermore, our approach achieved a personal best Precision and F-measure score of 32.7 and 25.5 respectively on the Semeval Keyphrase extraction challenge dataset. The paper describes the approaches used as well as the result obtained.1 © 2016 ACM.
12th International Conference on Semantic Systems, SEMANTiCS 2016
Leipzig; Spain
13 September 2016 through 14 September 2016
ACM International Conference Proceeding Series
Association for Computing Machinery
13-14-September-2016
57
62
9781450347525
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84994098413&doi=10.1145%2f2993318.2993323&partnerID=40&md5=9dc2a674fca209dbce1a88f10196e862
Decision trees; Extraction, F-measure scores; Key-phrase; Keyphrase extraction; Keyword extraction; Keywords; Random forest classifier; Random forests; Semantic features, Semantics; Keyphrase; Keywords; Random Forest
Adebayo, John Kolawole; Di Caro, Luigi; Boella, Guido
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: https://hdl.handle.net/2318/1639631
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 13
  • ???jsp.display-item.citation.isi??? ND
social impact