1 | | || ||Amharic ||Oromo ||Tigrinya ||Somali ||Norwegian ||Czech || |
2 | | ||capitalization || no || yes || no || yes || yes || yes || |
3 | | ||segmentation tool || [https://devadorner.northwestern.edu/maserver/wordtokenizer.html yes] || [https://devadorner.northwestern.edu/maserver/wordtokenizer.html yes] || [https://devadorner.northwestern.edu/maserver/wordtokenizer.html yes] || ? || [http://www.lrec-conf.org/proceedings/lrec2014/pdf/801_Paper.pdf yes] || yes || |
4 | | ||lemmatization tool || [http://www.aclweb.org/anthology/W07-0814 yes] || [http://www.cscjournals.org/manuscript/Journals/IJCL/volume1/Issue2/IJCL-6.pdf yes] || [http://www.aclweb.org/anthology/C12-3043 yes] || [https://ryantxanson.com/blog/somali-status yes] || [http://www.lrec-conf.org/proceedings/lrec2014/pdf/801_Paper.pdf yes] || yes || |
5 | | ||morphology tool || [http://www.cs.indiana.edu/~gasser/Research/software.html yes] || [http://www.cs.indiana.edu/~gasser/Research/software.html yes] || [http://www.cs.indiana.edu/~gasser/Research/software.html yes] || [https://ryantxanson.com/blog/somali-status yes] || [http://www.lrec-conf.org/proceedings/lrec2014/pdf/801_Paper.pdf yes] || yes || |
6 | | ||syllabification tool || ? || ? || ? || ? || [http://www.ushuaia.pl/hyphen/ yes] || [http://www.ushuaia.pl/hyphen/ yes] || |
7 | | ||POS || yes || [https://thesai.org/Downloads/SpecialIssueNo3/Paper%201-Parts%20of%20Speech%20Tagging%20for%20Afaan%20Oromo.pdf yes] || yes || yes || yes || yes || |
8 | | ||POS in Universal dep. || yes || no || no || no || no || yes || |
9 | | ||accents || no || no || no || no || yes || yes || |
10 | | ||no accents form || - || - || - || - || yes || yes || |
11 | | ||skript || Ethi || Latn || Ethi || Latn || Latn || Latn || |
12 | | ||ltr/rtl || ltr || ltr || ltr || ltr || ltr || ltr || |
13 | | ||no. of speakers || 21 811 600|| 17 468 100|| 6 915 000|| 14 762 900|| 4 741 780|| 10 619 340|| |
14 | | ||Wikipedia size (Sunday May 31, 2015) || 13 516|| 783|| 264|| 4 361|| 417 837|| 326 560|| |
15 | | ||ISO code || amh || orm || tir || som || nor || ces || |
16 | | ||Used in countries ||Ethiopia [ET] ||Etiopia, Kenya ||Eritrea [ER], Ethiopia [ET] ||Djibouti [DJ], Ethiopia [ET], Kenya [KE], Somalia [SO] ||Norway [NO] ||Czech Republic [CZ] || |
17 | | ||Language family ||Afro-Asiatic, Semitic, South, Ethiopian, South, Transversal, [[BR]]Amharic-Argobba ||Afro-Asiatic, Cushitic, East, Oromo ||Afro-Asiatic, Semitic, South, Ethiopian, North ||Afro-Asiatic, Cushitic, East, Somali ||Indo-European, Germanic, North, East Scandinavian, [[BR]]Danish-Swedish ||Indo-European, Balto-Slavic, Slavic, West, Czech-Slovak || |
18 | | || || || || || || || || |
19 | | || || || || || || || || |
20 | | || || || || || || || || |
21 | | || || || || || || || || |
22 | | ||'''Overlap of words in ethiopian languages (word source !http://crubadan.org/)''' || || || || || || || |
23 | | || || am || om || so || ti || || || |
24 | | || am || 50 000|| 0|| 0|| 3 660|| || || |
25 | | || om || 0|| 50 000|| 1 841|| 0|| || || |
26 | | || so || 0|| 1 841|| 50 000|| 0|| || || |
27 | | || ti || 3 660|| 0|| 0|| 50 000|| || || |
| 1 | || ||= Amharic =||= Oromo =||= Tigrinya =||= Somali =||= Norwegian =||= Czech =|| |
| 2 | ||=capitalization =|| no || yes || no || yes || yes || yes || |
| 3 | ||=segmentation tool =|| [https://devadorner.northwestern.edu/maserver/wordtokenizer.html yes] || [https://devadorner.northwestern.edu/maserver/wordtokenizer.html yes] || [https://devadorner.northwestern.edu/maserver/wordtokenizer.html yes] || ? || [http://www.lrec-conf.org/proceedings/lrec2014/pdf/801_Paper.pdf yes] || yes || |
| 4 | ||=lemmatization tool =|| [http://www.aclweb.org/anthology/W07-0814 yes] || [http://www.cscjournals.org/manuscript/Journals/IJCL/volume1/Issue2/IJCL-6.pdf yes] || [http://www.aclweb.org/anthology/C12-3043 yes] || [https://ryantxanson.com/blog/somali-status yes] || [http://www.lrec-conf.org/proceedings/lrec2014/pdf/801_Paper.pdf yes] || yes || |
| 5 | ||=morphology tool =|| [http://www.cs.indiana.edu/~gasser/Research/software.html yes] || [http://www.cs.indiana.edu/~gasser/Research/software.html yes] || [http://www.cs.indiana.edu/~gasser/Research/software.html yes] || [https://ryantxanson.com/blog/somali-status yes] || [http://www.lrec-conf.org/proceedings/lrec2014/pdf/801_Paper.pdf yes] || yes || |
| 6 | ||=syllabification tool =|| ? || ? || ? || ? || [http://www.ushuaia.pl/hyphen/ yes] || [http://www.ushuaia.pl/hyphen/ yes] || |
| 7 | ||=POS =|| yes || [https://thesai.org/Downloads/SpecialIssueNo3/Paper%201-Parts%20of%20Speech%20Tagging%20for%20Afaan%20Oromo.pdf yes] || yes || yes || yes || yes || |
| 8 | ||=POS in Universal dep. =|| yes || no || no || no || no || yes || |
| 9 | ||=accents =|| no || no || no || no || yes || yes || |
| 10 | ||=no accents form =|| - || - || - || - || yes || yes || |
| 11 | ||=script =|| Ethi || Latn || Ethi || Latn || Latn || Latn || |
| 12 | ||=ltr/rtl =|| ltr || ltr || ltr || ltr || ltr || ltr || |
| 13 | ||=no. of speakers =|| 21 811 600|| 17 468 100|| 6 915 000|| 14 762 900|| 4 741 780|| 10 619 340|| |
| 14 | ||=Wikipedia size (May 31, 2015) =|| 13 516|| 783|| 264|| 4 361|| 417 837|| 326 560|| |
| 15 | ||=ISO code =|| amh || orm || tir || som || nor || ces || |
| 16 | ||=Used in countries =||Ethiopia [ET] ||Etiopia, Kenya ||Eritrea [ER], Ethiopia [ET] ||Djibouti [DJ], Ethiopia [ET], Kenya [KE], Somalia [SO] =||Norway [NO] ||Czech Republic [CZ] || |
| 17 | ||=Language family =||Afro-Asiatic, Semitic, South, Ethiopian, South, Transversal, [[BR]]Amharic-Argobba ||Afro-Asiatic, Cushitic, East, Oromo ||Afro-Asiatic, Semitic, South, Ethiopian, North ||Afro-Asiatic, Cushitic, East, Somali ||Indo-European, Germanic, North, East Scandinavian, [[BR]]Danish-Swedish ||Indo-European, Balto-Slavic, Slavic, West, Czech-Slovak || |
| 18 | |
| 19 | |
| 20 | '''Overlap of words in ethiopian languages (word source !http://crubadan.org/)''' |
| 21 | |
| 22 | || ||= am =||= om =||= so =||= ti =|| |
| 23 | ||= am =|| 50 000|| 0|| 0|| 3 660|| |
| 24 | ||= om =|| 0|| 50 000|| 1 841|| 0|| |
| 25 | ||= so =|| 0|| 1 841|| 50 000|| 0|| |
| 26 | ||= ti =|| 3 660|| 0|| 0|| 50 000|| |