KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources

Giovanni Moretti; Rachele Sprugnoli; Sara Tonelli

doi:10.4000/books.aaccademia.1814

KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources

Giovanni Moretti
, Rachele Sprugnoli
, Sara Tonelli

Università Cattolica del Sacro Cuore

Fondazione Bruno Kessler

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents L-KD, a tool that relies on available linguistic and knowledge resources to perform keyphrase clustering and labelling. The aim of L-KD is to help finding and tracing themes in English and Italian text data, represented by groups of keyphrases and associated domains. We perform an evaluation of the top-ranked domains using the 20 Newsgroup dataset, and we show that 8 domains out of 10 match with manually assigned labels. This confirms the good accuracy of this approach, which does not require supervision.

Original language	English
Title of host publication	Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016)
Pages	216-221
Number of pages	6
Volume	1749
DOIs	https://doi.org/10.4000/books.aaccademia.1814
Publication status	Published - 2016
Event	Third Italian Conference on Computational Linguistics (CLiC-it 2016) - Napoli, Italia Duration: 5 Dec 2016 → 7 Dec 2016

Conference

Conference	Third Italian Conference on Computational Linguistics (CLiC-it 2016)
City	Napoli, Italia
Period	5/12/16 → 7/12/16

Keywords

computational linguistics, keyphrase extraction, clustering, wordnet domains, conceptnet

Access to Document

10.4000/books.aaccademia.1814

Cite this

Moretti, G., Sprugnoli, R., & Tonelli, S. (2016). KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources. In Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016) (Vol. 1749, pp. 216-221) https://doi.org/10.4000/books.aaccademia.1814

Moretti, Giovanni ; Sprugnoli, Rachele ; Tonelli, Sara. / KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources. Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016). Vol. 1749 2016. pp. 216-221

@inproceedings{e3044b042fa34a47957fb79ecda8a224,

title = "KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources",

abstract = "This paper presents L-KD, a tool that relies on available linguistic and knowledge resources to perform keyphrase clustering and labelling. The aim of L-KD is to help finding and tracing themes in English and Italian text data, represented by groups of keyphrases and associated domains. We perform an evaluation of the top-ranked domains using the 20 Newsgroup dataset, and we show that 8 domains out of 10 match with manually assigned labels. This confirms the good accuracy of this approach, which does not require supervision.",

keywords = "computational linguistics, keyphrase extraction, clustering, wordnet domains, conceptnet, computational linguistics, keyphrase extraction, clustering, wordnet domains, conceptnet",

author = "Giovanni Moretti and Rachele Sprugnoli and Sara Tonelli",

year = "2016",

doi = "10.4000/books.aaccademia.1814",

language = "English",

isbn = "9788899982089",

volume = "1749",

pages = "216--221",

booktitle = "Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) \& Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016)",

note = "Third Italian Conference on Computational Linguistics (CLiC-it 2016) ; Conference date: 05-12-2016 Through 07-12-2016",

}

Moretti, G, Sprugnoli, R & Tonelli, S 2016, KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources. in Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016). vol. 1749, pp. 216-221, Third Italian Conference on Computational Linguistics (CLiC-it 2016), Napoli, Italia, 5/12/16. https://doi.org/10.4000/books.aaccademia.1814

KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources. / Moretti, Giovanni; Sprugnoli, Rachele; Tonelli, Sara.
Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016). Vol. 1749 2016. p. 216-221.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources

AU - Moretti, Giovanni

AU - Sprugnoli, Rachele

AU - Tonelli, Sara

PY - 2016

Y1 - 2016

N2 - This paper presents L-KD, a tool that relies on available linguistic and knowledge resources to perform keyphrase clustering and labelling. The aim of L-KD is to help finding and tracing themes in English and Italian text data, represented by groups of keyphrases and associated domains. We perform an evaluation of the top-ranked domains using the 20 Newsgroup dataset, and we show that 8 domains out of 10 match with manually assigned labels. This confirms the good accuracy of this approach, which does not require supervision.

AB - This paper presents L-KD, a tool that relies on available linguistic and knowledge resources to perform keyphrase clustering and labelling. The aim of L-KD is to help finding and tracing themes in English and Italian text data, represented by groups of keyphrases and associated domains. We perform an evaluation of the top-ranked domains using the 20 Newsgroup dataset, and we show that 8 domains out of 10 match with manually assigned labels. This confirms the good accuracy of this approach, which does not require supervision.

KW - computational linguistics, keyphrase extraction, clustering, wordnet domains, conceptnet

UR - http://hdl.handle.net/10807/132966

UR - http://ceur-ws.org/vol-1749/paper38.pdf

UR - http://ceur-ws.org/vol-1749/

U2 - 10.4000/books.aaccademia.1814

DO - 10.4000/books.aaccademia.1814

M3 - Conference contribution

SN - 9788899982089

VL - 1749

SP - 216

EP - 221

BT - Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016)

T2 - Third Italian Conference on Computational Linguistics (CLiC-it 2016)

Y2 - 5 December 2016 through 7 December 2016

ER -

Moretti G, Sprugnoli R, Tonelli S. KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources. In Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016). Vol. 1749. 2016. p. 216-221 doi: 10.4000/books.aaccademia.1814

KD Strikes Back: from Keyphrases to Labelled Domains Using External Knowledge Sources

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this