Mining entities from the Web

Anna Lisa GentileAKSW Colloquium http://blog.aksw.org/

22nd June 2015

Web Technologies

Human Language Technologies

Knowledge Management Collective Intelligence

Text mining

Linked Open Data for Web-scale Information Extraction (LODIE)

• Web-scale IE– number of documents, domains, facts – exploit (semi-)structured content on the Web

• Linked Open Data to seed learning– “[...] a recommended best practice for exposing, sharing, and

connecting data [...] using URIs and RDF”(linkeddata.org)– a large KB of typed instances, relations, annotations (e.g.,

RDFa) • Adapting to specific user information needs

– users define specific IE tasks by specifying the types of instances and relations to be learnt

http://gow.epsrc.ac.uk/NGBOViewGrant.aspx?GrantRef=EP/J019488/1

Wrapper Induction

Wrapper Induction

LODIE Wrapper Induction methodDictionary Generation

– for each attribute ai,k of each concept ci, generate a dictionary di,k for ai,k by exploiting Linked Data

Page annotation – Wj,i Web pages from a website j containing entities of ci

– annotate pages in Wj,I by matching every entry in di,k against the text content in the leaf nodes

– for each match, create the pair < xpath,valuei,k > for Wj,I

Xpath identification – for each attribute, gather all xpaths of matching annotations and their matched

values– rate each path based on the number of different values it extracts – apply wpj,i,k best scoring xpath to re-annotate the website j for attribute ai,k

Dictionary Generation

• User Information Need formalisation– translate the concept and attributes of interest to the

vocabularies used within the Linked Data • given a SPARQL endpoint, query the exposed

Linked Data to identify the relevant concepts • select the most appropriate class and properties

that describe the attributes of interest • using the SPARQL endpoint, query the Linked Data

to retrieve instances of the properties of interest

Page annotation

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

Book Titles…Breakfast of ChampionsBreakfast on PlutoBreakheart PassBreaking Dawn…Breaking WindowsBreaking newsBreaking point…New Mexico SunriseNew Mexico SunsetNew MoonNew Orleans MourningNew Oxford Book of Austra…The Horus RoadThe HostThe Hostage Bride…

Frequent patterns identification

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]breaking dawn

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[10]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[3]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[6]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[8]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] breaking dawn/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[2]/A[1]/text()[1]

the host/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[3]/DIV[3]/UL[1]/LI[5]/A[1]/text()[1]

new moon

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/H2[1]/text()[1] 329

/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/DIV[1]/H2[1]/EM[1]/text()[1]329

…/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[2]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] 197/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[4]/TABLE[1]/TBODY[1]/TR[1]/TD[3]/B[1]/A[1]/text()[1] 193…/HTML[1]/BODY[1]/DIV[2]/DIV[2]/DIV[2]/DIV[1]/DIV[6]/P[1]/B[1]/text()[1]

1

INTUITIONuseful patterns will be likely to

match a larger variety of dictionary entries

Experiments

0.4 0.6 0.8 1.002468

10 t

isbnpd

p

aBook

F-measure

Number of

Websites

0.6 0.7 0.8 0.902468

10 mr tg t

Movie

F-measure

Number of

Websites

0.7 0.8 0.9 1.002468

10t

n

NBA player

F-measure

Number of

Websites

0.55 0.6 0.65 0.7 0.75 0.8 0.8502468

10c n

Restaurant

F-measure

Number of

Websites

0.65 0.7 0.75 0.8 0.85 0.9 0.95 102468

10

w

nUniversity

F-measure

Number of

Websites

http://dl.acm.org/citation.cfm?doid=2479832.2479845

PapersAI Magazine 2015 Gentile, Anna Lisa, Zhang, Ziqi, and Ciravegna, Fabio(2015). Early Steps Towards Web Scale Information Extraction with LODIE. AI Magazine, 36(1), 55--64.http://www.aaai.org/ojs/index.php/aimagazine/article/view/2567

KCAP 2013Gentile, Anna Lisa, Zhang, Ziqi, Augenstein, Isabelle, and Ciravegna, Fabio (2013). Unsupervised wrapper induction using linked data. Proceedings of the seventh international conference on Knowledge capture, 41--48. Banff, Canada: ACMhttp://dl.acm.org/citation.cfm?doid=2479832.2479845

TSD 2014Gentile, Anna Lisa, Zhang, Ziqi, and Ciravegna, Fabio (2014). Self Training Wrapper Induction with Linked Data. Text, Speech and Dialogue - 17th International Conference, {TSD} 2014, Brno, Czech Republic, September 8-12, 2014. Proceedings, 285--292.http://link.springer.com/chapter/10.1007%2F978-3-319-10816-2_35 the PREPRINT is here: http://www.tsdconference.org/tsd2014/download/preprints/681.pdf

ISWC 2014Gentile, Anna Lisa and Mazumdar, Suvodeep (2014). User driven Information Extraction with LODIE. Proceedings of the ISWC 2014 Posters & Demonstrations Track a track within the 13th International Semantic Web Conference (ISWC 2014), 385-388.http://ceur-ws.org/Vol-1272/paper_112.pdf Demohttp://staffwww.dcs.shef.ac.uk/people/A.L.Gentile/demo/iswc2014.html