μRaptor: A DOM-based system with appetite for hCard elements

Emir Muñoz; Luca Costabello; Pierre Yves Vandenbussche

μRaptor: A DOM-based system with appetite for hCard elements

Emir Muñoz, Luca Costabello, Pierre Yves Vandenbussche

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper describes μRaptor, a DOM-based method to extract hCard microformats from HTML pages stripped of microformat markup. μRaptor extracts DOM sub-trees, converts them into rules, and uses them to extract hCard microformats. Besides, we use co-occurring CSS classes to improve the overall precision. Results on train data show 0.96 precision and 0.83 F₁ measure by considering only the most common tree patterns. Furthermore, we propose the adoption of additional constraint rules on the values of hCard elements to further improve the extraction.

Original language	English
Pages (from-to)	67-71
Number of pages	5
Journal	CEUR Workshop Proceedings
Volume	1267
State	Published - 2014
Externally published	Yes
Event	2nd International Workshop on Linked Data for Information Extraction, LD4IE 2014, Co-located with the 13th International Semantic Web Conference, ISWC 2014 - Riva del Garda, Italy Duration: Oct 20 2014 → …

Cite this

@article{9865a376c242411981eff58a2aa7566b,

title = "μRaptor: A DOM-based system with appetite for hCard elements",

abstract = "This paper describes μRaptor, a DOM-based method to extract hCard microformats from HTML pages stripped of microformat markup. μRaptor extracts DOM sub-trees, converts them into rules, and uses them to extract hCard microformats. Besides, we use co-occurring CSS classes to improve the overall precision. Results on train data show 0.96 precision and 0.83 F1 measure by considering only the most common tree patterns. Furthermore, we propose the adoption of additional constraint rules on the values of hCard elements to further improve the extraction.",

author = "Emir Mu{\~n}oz and Luca Costabello and Vandenbussche, {Pierre Yves}",

year = "2014",

language = "Ingl{\'e}s",

volume = "1267",

pages = "67--71",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

note = "2nd International Workshop on Linked Data for Information Extraction, LD4IE 2014, Co-located with the 13th International Semantic Web Conference, ISWC 2014 ; Conference date: 20-10-2014",

}

TY - JOUR

T1 - μRaptor

T2 - 2nd International Workshop on Linked Data for Information Extraction, LD4IE 2014, Co-located with the 13th International Semantic Web Conference, ISWC 2014

AU - Muñoz, Emir

AU - Costabello, Luca

AU - Vandenbussche, Pierre Yves

PY - 2014

Y1 - 2014

N2 - This paper describes μRaptor, a DOM-based method to extract hCard microformats from HTML pages stripped of microformat markup. μRaptor extracts DOM sub-trees, converts them into rules, and uses them to extract hCard microformats. Besides, we use co-occurring CSS classes to improve the overall precision. Results on train data show 0.96 precision and 0.83 F1 measure by considering only the most common tree patterns. Furthermore, we propose the adoption of additional constraint rules on the values of hCard elements to further improve the extraction.

AB - This paper describes μRaptor, a DOM-based method to extract hCard microformats from HTML pages stripped of microformat markup. μRaptor extracts DOM sub-trees, converts them into rules, and uses them to extract hCard microformats. Besides, we use co-occurring CSS classes to improve the overall precision. Results on train data show 0.96 precision and 0.83 F1 measure by considering only the most common tree patterns. Furthermore, we propose the adoption of additional constraint rules on the values of hCard elements to further improve the extraction.

UR - http://www.scopus.com/inward/record.url?scp=84939796513&partnerID=8YFLogxK

M3 - Artículo de la conferencia

AN - SCOPUS:84939796513

SN - 1613-0073

VL - 1267

SP - 67

EP - 71

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 20 October 2014

ER -

μRaptor: A DOM-based system with appetite for hCard elements

Abstract

Other files and links

Fingerprint

Cite this