%PDF-1.3
3 0 obj
<</Type /Page
/Parent 1 0 R
/Resources 2 0 R
/Annots [<</Type /Annot /Subtype /Link /Rect [102.05 767.10 267.35 755.10] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012)>>>><</Type /Annot /Subtype /Link /Rect [31.18 21.01 72.53 13.01] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012)>>>><</Type /Annot /Subtype /Link /Rect [102.05 767.10 267.35 755.10] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012)>>>><</Type /Annot /Subtype /Link /Rect [31.18 21.01 72.53 13.01] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012)>>>>]
/Contents 4 0 R>>
endobj
4 0 obj
<</Length 1089>>
stream
2 J
0.57 w
0.85 w
19.84 807.87 m 575.44 807.87 l S
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 826.13 Td (LREC 2012 Language Library) Tj ET Q
0.57 w
BT /F2 12.00 Tf ET
q 0.000 g BT 102.05 780.18 Td (LREC 2012) Tj ET Q
q 0.000 0.000 1.000 rg BT 102.05 757.50 Td (http://www.lrec-conf.org/lrec2012) Tj ET 102.05 756.30 165.30 -0.60 re f Q
BT /F3 14.00 Tf ET
q 0.000 g BT 297.64 568.40 Td () Tj ET Q
BT /F4 22.00 Tf ET
q 0.000 g BT 144.81 636.86 Td (LREC 2012 Language Library) Tj ET Q
BT /F1 8.00 Tf ET
q 0.000 g BT 261.19 599.96 Td (- Final Submission - ) Tj ET Q
BT /F2 12.00 Tf ET
q 0.000 g BT 314.65 308.21 Td (Hélène Mazo) Tj ET Q
BT /F2 10.00 Tf ET
BT /F2 12.00 Tf ET
q 0.000 g BT 314.65 274.20 Td (Published : Wednesday 28 September 2011) Tj ET Q
BT /F2 11.00 Tf ET
q 0.000 g BT 314.65 257.49 Td (Modified : Monday 20 February 2012) Tj ET Q
BT /F2 10.00 Tf ET
q 0.000 g BT 314.65 240.78 Td (Created : Wednesday 27 September 2017) Tj ET Q
0.85 w
19.84 25.51 m 575.44 25.51 l S
BT /F5 8.00 Tf ET
q 0.000 g BT 31.18 14.61 Td (LREC 2012) Tj ET Q
q 0.000 g BT 524.77 14.61 Td (Page 1/3) Tj ET Q

endstream
endobj
5 0 obj
<</Type /Page
/Parent 1 0 R
/Resources 2 0 R
/Annots [<</Type /Annot /Subtype /Link /Rect [236.27 743.43 342.97 733.43] /Border [0 0 0] /A <</S /URI /URI (http://www.languagelibrary.eu)>>>><</Type /Annot /Subtype /Link /Rect [271.31 396.18 297.43 386.18] /Border [0 0 0] /A <</S /URI /URI (http://www.elra.info)>>>><</Type /Annot /Subtype /Link /Rect [501.40 176.50 538.07 166.50] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012/#)>>>><</Type /Annot /Subtype /Link /Rect [31.18 21.01 72.53 13.01] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012)>>>><</Type /Annot /Subtype /Link /Rect [236.27 743.43 342.97 733.43] /Border [0 0 0] /A <</S /URI /URI (http://www.languagelibrary.eu)>>>><</Type /Annot /Subtype /Link /Rect [271.31 396.18 297.43 386.18] /Border [0 0 0] /A <</S /URI /URI (http://www.elra.info)>>>><</Type /Annot /Subtype /Link /Rect [501.40 176.50 538.07 166.50] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012/#)>>>><</Type /Annot /Subtype /Link /Rect [31.18 21.01 72.53 13.01] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012)>>>>]
/Contents 6 0 R>>
endobj
6 0 obj
<</Length 5136>>
stream
2 J
0.57 w
BT /F2 10.00 Tf ET
0.85 w
19.84 807.87 m 575.44 807.87 l S
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 826.13 Td (LREC 2012 Language Library) Tj ET Q
0.57 w
BT /F2 10.00 Tf ET
BT /F1 10.00 Tf ET
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 770.86 Td (Help for the Language Library) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 735.43 Td (The Language Library is currently available at) Tj ET Q
q 0.000 g BT 233.49 735.43 Td ( ) Tj ET Q
q 0.000 0.000 1.000 rg BT 236.27 735.43 Td (www.languagelibrary.eu) Tj ET 236.27 734.43 106.70 -0.50 re f Q
q 0.000 g BT 342.97 735.43 Td (.) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 699.99 Td (Motivation) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 664.56 Td (The Language Library is the new feature of LREC 2012. The rationale behind this initiative is that accumulation of) Tj ET Q
q 0.000 g BT 31.18 650.39 Td (massive amounts of multi-dimensional data about language is the key to foster advancement in our knowledge about) Tj ET Q
q 0.000 g BT 31.18 636.21 Td (language and its mechanisms. The objective is to gather and share part of the linguistic knowledge the field is able to) Tj ET Q
q 0.000 g BT 31.18 622.04 Td (produce, starting a movement aimed at collecting all possible annotations/encodings at all possible levels.) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 586.61 Td (As a first experiment of a community-built repository) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 282.90 586.61 Td ( that allows sharing of multidimensional and multi-level) Tj ET Q
q 0.000 g BT 31.18 572.43 Td (processed/annotated resources,) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 174.03 572.43 Td ( it needs a small effort from each of you) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 362.97 572.43 Td ( to put into place new ways of collaboration) Tj ET Q
q 0.000 g BT 31.18 558.26 Td (within the language resources and technology community.) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 522.83 Td (Download the data to be processed) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 487.39 Td (You can download the processable data from the START submission page and you are invited to process the data using) Tj ET Q
q 0.000 g BT 31.18 473.22 Td (the tools you are working on/have available.) Tj ET Q
q 0.000 g BT 31.18 437.79 Td (For the Written modality, raw data has been chosen from small Wikipedia entries and the Universal Declaration of) Tj ET Q
q 0.000 g BT 31.18 423.61 Td (Human Rights in several languages \(providing both comparable and parallel data\).) Tj ET Q
q 0.000 g BT 31.18 388.18 Td (For the Speech modality, data have been provided by) Tj ET Q
q 0.000 g BT 268.53 388.18 Td ( ) Tj ET Q
q 0.000 0.000 1.000 rg BT 271.31 388.18 Td (ELRA) Tj ET 271.31 387.18 26.12 -0.50 re f Q
q 0.000 g BT 297.43 388.18 Td ( . They consist of brief audio samples of broadcast news,) Tj ET Q
q 0.000 g BT 31.18 374.01 Td (telephone speech etc. They are available for a limited number of languages \(here the list of languages\).) Tj ET Q
q 0.000 g BT 31.18 338.58 Td (From the LREC2012 Language Library section of the START Submission page, you are invited to proceed as follows:) Tj ET Q
q 0.000 g BT 34.10 310.23 Td (1.) Tj ET Q
q 0.000 g BT 51.02 310.23 Td ( Confirm your interest in contributing to the Language Library by checking I wish to contribute \(its important that) Tj ET Q
q 0.000 g BT 51.02 296.06 Td (you do this as soon as you know that you are willing to process some data\).) Tj ET Q
q 0.000 g BT 34.10 281.88 Td (2.) Tj ET Q
q 0.000 g BT 51.02 281.88 Td ( Select the modality and language\(s\) you would like to process; alternatively, you can choose to download the full) Tj ET Q
q 0.000 g BT 51.02 267.71 Td (raw data set using the) Tj ET Q
BT /F5 10.00 Tf ET
q 0.000 g BT 148.85 267.71 Td ( Download All) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 209.98 267.71 Td ( button.) Tj ET Q
q 0.000 g BT 34.10 253.54 Td (3.) Tj ET Q
q 0.000 g BT 51.02 253.54 Td ( Download the data: you can download the raw data and upload the processed data until the final paper submission) Tj ET Q
q 0.000 g BT 51.02 239.36 Td (deadline.) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 203.93 Td (Contributing new processable data) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 168.50 Td (Not all languages, neither all modalities, are covered by the LREC 2012 raw data. Please send an email to) Tj ET Q
q 0.000 0.000 1.000 rg BT 501.40 168.50 Td ( [E-mail]) Tj ET 501.40 167.50 36.67 -0.50 re f Q
q 0.000 g BT 538.07 168.50 Td ( if) Tj ET Q
q 0.000 g BT 31.18 154.32 Td (you cannot find the language\(s\) you work on, or if you want to contribute to the Library with other raw \(or raw and) Tj ET Q
q 0.000 g BT 31.18 140.15 Td (processed\) data to be made available to all.) Tj ET Q
q 0.000 g BT 31.18 104.72 Td (Important:) Tj ET 31.18 103.72 45.02 -0.50 re f Q
q 0.000 g BT 76.20 104.72 Td ( Data provided must not be copyrighted.) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 69.28 Td (Process and upload the data) Tj ET Q
BT /F1 10.00 Tf ET
0.85 w
19.84 25.51 m 575.44 25.51 l S
BT /F5 8.00 Tf ET
q 0.000 g BT 31.18 14.61 Td (LREC 2012) Tj ET Q
q 0.000 g BT 524.77 14.61 Td (Page 2/3) Tj ET Q

endstream
endobj
7 0 obj
<</Type /Page
/Parent 1 0 R
/Resources 2 0 R
/Annots [<</Type /Annot /Subtype /Link /Rect [174.02 374.92 207.91 364.92] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012/#)>>>><</Type /Annot /Subtype /Link /Rect [174.02 374.92 207.91 364.92] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012/#)>>>><</Type /Annot /Subtype /Link /Rect [31.18 21.01 72.53 13.01] /Border [0 0 0] /A <</S /URI /URI (http://www.lrec-conf.org/lrec2012)>>>>]
/Contents 8 0 R>>
endobj
8 0 obj
<</Length 3801>>
stream
2 J
0.57 w
BT /F1 10.00 Tf ET
0.85 w
19.84 807.87 m 575.44 807.87 l S
q 0.000 g BT 31.18 826.13 Td (LREC 2012 Language Library) Tj ET Q
0.57 w
q 0.000 g BT 31.18 792.12 Td (Processing and uploading the data can be done for at least 1 month after paper submission deadline:) Tj ET Q
q 0.000 g BT 34.10 763.77 Td (1.) Tj ET Q
q 0.000 g BT 51.02 763.77 Td ( Process/annotate the data using the tools and type of processing/annotation you are working on.) Tj ET Q
q 0.000 g BT 34.10 749.60 Td (2.) Tj ET Q
q 0.000 g BT 51.02 749.60 Td ( For) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 68.80 749.60 Td ( Written) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 106.02 749.60 Td ( data: Please) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 164.39 749.60 Td ( process/annotate plain text files without changing/deleting any part of it) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 508.91 749.60 Td (. This is) Tj ET Q
q 0.000 g BT 51.02 735.43 Td (important in order to preserve the integrity and the comparability of the processed/annotated data. Most specifically,) Tj ET Q
q 0.000 g BT 51.02 721.25 Td (if you want to provide stand-off annotation the offsets should refer to the plain texts.   Notice that for each Wikipedia) Tj ET Q
q 0.000 g BT 51.02 707.08 Td (entry we provide, in addition to the plain text file which you are asked to process as it is, also the source HTML as) Tj ET Q
q 0.000 g BT 51.02 692.91 Td (reference only.) Tj ET Q
q 0.000 g BT 117.16 692.91 Td ( For Speech data: please dont change/split the input audio samples.) Tj ET 117.16 691.91 304.06 -0.50 re f Q
q 0.000 g BT 34.10 678.73 Td (3.) Tj ET Q
q 0.000 g BT 51.02 678.73 Td ( The only requirement we ask is to keep track of which plain text files were used to produce each output file you are) Tj ET Q
q 0.000 g BT 51.02 664.56 Td (going to upload. Should your tool rename input files, please keep the mapping between old and new names) Tj ET Q
q 0.000 g BT 51.02 650.39 Td (because you will need it when you submit processed data) Tj ET Q
q 0.000 g BT 34.10 636.21 Td (4.) Tj ET Q
q 0.000 g BT 51.02 636.21 Td ( Provide some basic metadata information upon upload \(we will recommend some basic metadata\).) Tj ET Q
q 0.000 g BT 34.10 622.04 Td (5.) Tj ET Q
q 0.000 g BT 51.02 622.04 Td ( Upload the processed data \(of any kind and in any format\).) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 313.93 622.04 Td ( You will receive instructions by email on where and) Tj ET Q
q 0.000 g BT 51.02 607.87 Td (how to submit your processed data) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 219.39 607.87 Td ( \(a mail will be sent to those declaring their willingness to contribute and) Tj ET Q
q 0.000 g BT 51.02 593.69 Td (download some raw data\).) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 558.26 Td (Availability to all) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 522.83 Td (All the processed data will be available to everyone before LREC in a special LREC Repository.) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 487.39 Td (Licensing) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 451.96 Td (Wikipedia entries are available under the Creative Commons Attribution-ShareAlike License.) Tj ET Q
BT /F4 10.00 Tf ET
q 0.000 g BT 31.18 416.53 Td (Send us comments) Tj ET Q
BT /F1 10.00 Tf ET
q 0.000 g BT 31.18 381.09 Td (Given the experimental nature of the Library we are very interested in receiving your comments and suggestions to) Tj ET Q
q 0.000 g BT 31.18 366.92 Td (improve it! Please send them to) Tj ET Q
q 0.000 g BT 171.24 366.92 Td ( ) Tj ET Q
q 0.000 0.000 1.000 rg BT 174.02 366.92 Td ([E-mail]) Tj ET 174.02 365.92 33.89 -0.50 re f Q
q 0.000 g BT 207.91 366.92 Td (.) Tj ET Q
BT /F5 8.00 Tf ET
0.85 w
19.84 25.51 m 575.44 25.51 l S
q 0.000 g BT 31.18 14.61 Td (LREC 2012) Tj ET Q
q 0.000 g BT 524.77 14.61 Td (Page 3/3) Tj ET Q

endstream
endobj
1 0 obj
<</Type /Pages
/Kids [3 0 R 5 0 R 7 0 R ]
/Count 3
/MediaBox [0 0 595.28 841.89]
>>
endobj
9 0 obj
<</Type /Font
/BaseFont /Helvetica
/Subtype /Type1
/Encoding /WinAnsiEncoding
>>
endobj
10 0 obj
<</Type /Font
/BaseFont /Times-Roman
/Subtype /Type1
/Encoding /WinAnsiEncoding
>>
endobj
11 0 obj
<</Type /Font
/BaseFont /Courier-Bold
/Subtype /Type1
/Encoding /WinAnsiEncoding
>>
endobj
12 0 obj
<</Type /Font
/BaseFont /Helvetica-Bold
/Subtype /Type1
/Encoding /WinAnsiEncoding
>>
endobj
13 0 obj
<</Type /Font
/BaseFont /Helvetica-Oblique
/Subtype /Type1
/Encoding /WinAnsiEncoding
>>
endobj
2 0 obj
<<
/ProcSet [/PDF /Text /ImageB /ImageC /ImageI]
/Font <<
/F1 9 0 R
/F2 10 0 R
/F3 11 0 R
/F4 12 0 R
/F5 13 0 R
>>
/XObject <<
>>
>>
endobj
14 0 obj
<<
/Producer (FPDF 1.53)
/Title (LREC 2012 Language Library)
/Subject (Final Submission)
/Creator (LREC 2012)
/CreationDate (D:20170927162056)
>>
endobj
15 0 obj
<<
/Type /Catalog
/Pages 1 0 R
/OpenAction [3 0 R /Fit]
/PageLayout /SinglePage
>>
endobj
xref
0 16
0000000000 65535 f 
0000012491 00000 n 
0000013092 00000 n 
0000000009 00000 n 
0000000646 00000 n 
0000001785 00000 n 
0000002948 00000 n 
0000008134 00000 n 
0000008640 00000 n 
0000012590 00000 n 
0000012686 00000 n 
0000012785 00000 n 
0000012885 00000 n 
0000012987 00000 n 
0000013240 00000 n 
0000013402 00000 n 
trailer
<<
/Size 16
/Root 15 0 R
/Info 14 0 R
>>
startxref
13501
%%EOF